update tags

contrib fix
contrib
2025-10-04 12:10:43 -04:00 · 2025-10-04 11:53:48 -04:00 · 2025-10-04 11:47:56 -04:00 · 2025-10-04 11:26:10 -04:00 · 2025-10-04 09:48:19 -04:00 · 2025-10-04 09:07:22 -04:00
338 changed files with 10229 additions and 20593 deletions
--- a/.coveragerc
+++ b/.coveragerc
@@ -2,7 +2,6 @@
 source = axolotl
 omit =
    */tests/*
-    setup.py

 [report]
 exclude_lines =
--- a/.github/CONTRIBUTING.md
+++ b/.github/CONTRIBUTING.md
@@ -29,13 +29,18 @@ PRs are **greatly welcome**!
 2. Set up the development environment by following the instructions in the [README.md](https://github.com/axolotl-ai-cloud/axolotl/tree/main/README.md) file.
 3. Explore the codebase, run tests, and verify that everything works as expected.

-Please run below to setup env
-```bash
-pip3 install -r requirements-dev.txt -r requirements-tests.txt
-pre-commit install
+Please run the below to setup:

-# test
-pytest tests/
+```bash
+git clone https://github.com/axolotl-ai-cloud/axolotl.git
+cd axolotl
+
+uv sync --dev && uv pip install flash-attn --no-build-isolation
+source .venv/bin/activate
+
+pre-commit install  # install pre-commit hooks
+
+pytest tests/  # optional; run test suite
 ```

 ## How to Contribute
--- a/.github/FUNDING.yml
+++ b/.github/FUNDING.yml
@@ -1,13 +1,13 @@
 # These are supported funding model platforms

-github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+github: [winglian, OpenAccess-AI-Collective] # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
 patreon: # Replace with a single Patreon username
 open_collective: # Replace with a single Open Collective username
-ko_fi: # Replace with a single Ko-fi username
+ko_fi: axolotl_ai # Replace with a single Ko-fi username
 tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
 community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
 liberapay: # Replace with a single Liberapay username
 issuehunt: # Replace with a single IssueHunt username
 otechie: # Replace with a single Otechie username
 lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
-custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']
+custom: ['https://quickchart.io/qr?text=bitcoin%3Abc1qxlgwlqwfea5s2cxm42xqsfmwjct0rj8w8ea5np&size=480&centerImageUrl=https%3A%2F%2Fupload.wikimedia.org%2Fwikipedia%2Fcommons%2Fthumb%2F4%2F46%2FBitcoin.svg%2F64px-Bitcoin.svg.png'] # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']
--- a/.github/PULL_REQUEST_TEMPLATE.md
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@@ -15,11 +15,6 @@
 <!--- Include details of your testing environment, tests ran to see how -->
 <!--- your change affects other areas of the code, etc. -->

-## AI Usage Disclaimer
-
-<!--- Was AI (e.g., ChatGPT, Claude, Copilot) used to generate or assist with this PR? -->
-<!--- Please indicate: No / Yes (specify which tool and to what extent) -->
-
 ## Screenshots (if appropriate)

 ## Types of changes
--- a/.github/workflows/base.yml
+++ b/.github/workflows/base.yml
@@ -21,12 +21,38 @@ jobs:
    timeout-minutes: 480
    # this job needs to be run on self-hosted GPU runners...
    runs-on: ubuntu-latest-m
-    env:
-      HAS_DOCKERHUB_CREDS: ${{ secrets.DOCKERHUB_USERNAME != '' && secrets.DOCKERHUB_TOKEN != '' }}
    strategy:
      fail-fast: false
      matrix:
        include:
+          - cuda: "124"
+            cuda_version: 12.4.1
+            cudnn_version: ""
+            python_version: "3.11"
+            pytorch: 2.6.0
+            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
+            dockerfile: "Dockerfile-base"
+          - cuda: "126"
+            cuda_version: 12.6.3
+            cudnn_version: ""
+            python_version: "3.11"
+            pytorch: 2.6.0
+            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
+            dockerfile: "Dockerfile-base"
+          - cuda: "126"
+            cuda_version: 12.6.3
+            cudnn_version: ""
+            python_version: "3.11"
+            pytorch: 2.7.1
+            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
+            dockerfile: "Dockerfile-base"
+          - cuda: "128"
+            cuda_version: 12.8.1
+            cudnn_version: ""
+            python_version: "3.11"
+            pytorch: 2.7.1
+            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
+            dockerfile: "Dockerfile-base"
          - cuda: "128"
            cuda_version: 12.8.1
            cudnn_version: ""
@@ -34,47 +60,6 @@ jobs:
            pytorch: 2.8.0
            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
            dockerfile: "Dockerfile-base"
-            platforms: "linux/amd64"
-          - cuda: "128"
-            cuda_version: 12.8.1
-            cudnn_version: ""
-            python_version: "3.11"
-            pytorch: 2.9.0
-            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
-            dockerfile: "Dockerfile-base"
-            platforms: "linux/amd64,linux/arm64"
-          - cuda: "128"
-            cuda_version: 12.8.1
-            cudnn_version: ""
-            python_version: "3.11"
-            pytorch: 2.9.1
-            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
-            dockerfile: "Dockerfile-base"
-            platforms: "linux/amd64,linux/arm64"
-          - cuda: "129"
-            cuda_version: 12.9.1
-            cudnn_version: ""
-            python_version: "3.12"
-            pytorch: 2.9.1
-            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
-            dockerfile: "Dockerfile-base"
-            platforms: "linux/amd64,linux/arm64"
-          - cuda: "130"
-            cuda_version: 13.0.0
-            cudnn_version: ""
-            python_version: "3.11"
-            pytorch: 2.9.1
-            torch_cuda_arch_list: "9.0+PTX"
-            dockerfile: "Dockerfile-base"
-            platforms: "linux/amd64,linux/arm64"
-          - cuda: "130"
-            cuda_version: 13.0.0
-            cudnn_version: ""
-            python_version: "3.12"
-            pytorch: 2.9.1
-            torch_cuda_arch_list: "9.0+PTX"
-            dockerfile: "Dockerfile-base"
-            platforms: "linux/amd64,linux/arm64"
 #          - cuda: "128"
 #            cuda_version: 12.8.1
 #            cudnn_version: ""
@@ -98,10 +83,10 @@ jobs:
        uses: docker/metadata-action@v5
        with:
          images: |
+            winglian/axolotl-base
            axolotlai/axolotl-base
      - name: Login to Docker Hub
        uses: docker/login-action@v2
-        if: ${{ github.event_name != 'pull_request' && env.HAS_DOCKERHUB_CREDS == 'true' }}
        with:
          username: ${{ secrets.DOCKERHUB_USERNAME }}
          password: ${{ secrets.DOCKERHUB_TOKEN }}
@@ -112,9 +97,10 @@ jobs:
        with:
          context: .
          file: ./docker/${{ matrix.dockerfile }}
-          platforms: ${{ matrix.platforms }}
          push: ${{ github.event_name != 'pull_request' }}
-          tags: ${{ steps.metadata.outputs.tags }}-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+          tags: |
+            ${{ steps.metadata.outputs.tags }}-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+            ${{ steps.metadata.outputs.tags }}-base-uv-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
          labels: ${{ steps.metadata.outputs.labels }}
          build-args: |
            CUDA_VERSION=${{ matrix.cuda_version }}
@@ -127,12 +113,31 @@ jobs:
    if: ${{ github.repository_owner == 'axolotl-ai-cloud' && (github.event_name != 'pull_request' || !github.event.pull_request.draft) }}
    timeout-minutes: 480
    runs-on: ubuntu-latest-m
-    env:
-      HAS_DOCKERHUB_CREDS: ${{ secrets.DOCKERHUB_USERNAME != '' && secrets.DOCKERHUB_TOKEN != '' }}
    strategy:
      fail-fast: false
      matrix:
        include:
+          - cuda: "126"
+            cuda_version: 12.6.3
+            cudnn_version: ""
+            python_version: "3.11"
+            pytorch: 2.6.0
+            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
+            dockerfile: "Dockerfile-uv-base"
+          - cuda: "126"
+            cuda_version: 12.6.3
+            cudnn_version: ""
+            python_version: "3.11"
+            pytorch: 2.7.1
+            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
+            dockerfile: "Dockerfile-uv-base"
+          - cuda: "128"
+            cuda_version: 12.8.1
+            cudnn_version: ""
+            python_version: "3.11"
+            pytorch: 2.7.1
+            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
+            dockerfile: "Dockerfile-uv-base"
          - cuda: "128"
            cuda_version: 12.8.1
            cudnn_version: ""
@@ -140,47 +145,6 @@ jobs:
            pytorch: 2.8.0
            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
            dockerfile: "Dockerfile-uv-base"
-            platforms: "linux/amd64"
-          - cuda: "128"
-            cuda_version: 12.8.1
-            cudnn_version: ""
-            python_version: "3.11"
-            pytorch: 2.9.1
-            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
-            dockerfile: "Dockerfile-uv-base"
-            platforms: "linux/amd64,linux/arm64"
-          - cuda: "128"
-            cuda_version: 12.8.1
-            cudnn_version: ""
-            python_version: "3.11"
-            pytorch: 2.9.0
-            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
-            dockerfile: "Dockerfile-uv-base"
-            platforms: "linux/amd64,linux/arm64"
-          - cuda: "129"
-            cuda_version: 12.9.1
-            cudnn_version: ""
-            python_version: "3.12"
-            pytorch: 2.9.1
-            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
-            dockerfile: "Dockerfile-uv-base"
-            platforms: "linux/amd64,linux/arm64"
-          - cuda: "130"
-            cuda_version: 13.0.0
-            cudnn_version: ""
-            python_version: "3.11"
-            pytorch: 2.9.1
-            torch_cuda_arch_list: "9.0+PTX"
-            dockerfile: "Dockerfile-uv-base"
-            platforms: "linux/amd64,linux/arm64"
-          - cuda: "130"
-            cuda_version: 13.0.0
-            cudnn_version: ""
-            python_version: "3.12"
-            pytorch: 2.9.1
-            torch_cuda_arch_list: "9.0+PTX"
-            dockerfile: "Dockerfile-uv-base"
-            platforms: "linux/amd64,linux/arm64"
    steps:
      - name: Checkout
        uses: actions/checkout@v4
@@ -192,7 +156,6 @@ jobs:
            axolotlai/axolotl-base-uv
      - name: Login to Docker Hub
        uses: docker/login-action@v2
-        if: ${{ github.event_name != 'pull_request' && env.HAS_DOCKERHUB_CREDS == 'true' }}
        with:
          username: ${{ secrets.DOCKERHUB_USERNAME }}
          password: ${{ secrets.DOCKERHUB_TOKEN }}
@@ -203,7 +166,6 @@ jobs:
        with:
          context: .
          file: ./docker/${{ matrix.dockerfile }}
-          platforms: ${{ matrix.platforms }}
          push: ${{ github.event_name != 'pull_request' }}
          tags: ${{ steps.metadata.outputs.tags }}-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
          labels: ${{ steps.metadata.outputs.labels }}
--- a/.github/workflows/docs.yml
+++ b/.github/workflows/docs.yml
@@ -12,9 +12,6 @@ jobs:
    build-deploy:
        runs-on: ubuntu-latest
        steps:
-        - name: cleanup node
-          run: |
-            sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL
        - name: Check out repository
          uses: actions/checkout@v4
        - name: Set up Quarto
@@ -23,10 +20,14 @@ jobs:
          uses: actions/setup-python@v5
          with:
            python-version: '3.11'
+        - name: Install uv
+          uses: astral-sh/setup-uv@v4
+          with:
+            version: "latest"
        - name: Install dependencies
          run: |
-            python3 -m pip install jupyter quartodoc
-            python3 -m pip install -e .
+            uv pip install --system jupyter quartodoc
+            uv pip install --system -e .
        - name: Build autodoc
          run: quartodoc build
        - name: Publish to GitHub Pages (and render)
--- a/.github/workflows/lint.yml
+++ b/.github/workflows/lint.yml
@@ -6,7 +6,7 @@ on:
      types: [opened, synchronize, reopened, ready_for_review]
      paths:
       - '**.py'
-       - 'requirements.txt'
+       - 'pyproject.toml'
       - '.github/workflows/*.yml'
       - "*.[q]md"
       - "examples/**/*.y[a]?ml"
@@ -23,5 +23,4 @@ jobs:
      - uses: actions/setup-python@v5
        with:
          python-version: "3.11"
-          cache: 'pip' # caching pip dependencies
      - uses: pre-commit/action@v3.0.1
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -15,37 +15,27 @@ jobs:
      fail-fast: false
      matrix:
        include:
+          - cuda: 126
+            cuda_version: 12.6.3
+            python_version: "3.11"
+            pytorch: 2.6.0
+            axolotl_extras:
+          - cuda: 126
+            cuda_version: 12.6.3
+            python_version: "3.11"
+            pytorch: 2.7.1
+            axolotl_extras: vllm
+            is_latest: true
+          - cuda: 128
+            cuda_version: 12.8.1
+            python_version: "3.11"
+            pytorch: 2.7.1
+            axolotl_extras:
          - cuda: 128
            cuda_version: 12.8.1
            python_version: "3.11"
            pytorch: 2.8.0
            axolotl_extras:
-            platforms: "linux/amd64"
-          - cuda: 128
-            cuda_version: 12.8.1
-            python_version: "3.11"
-            pytorch: 2.9.0
-            axolotl_extras:
-            platforms: "linux/amd64,linux/arm64"
-          - cuda: 128
-            cuda_version: 12.8.1
-            python_version: "3.11"
-            pytorch: 2.9.1
-            axolotl_extras:
-            platforms: "linux/amd64,linux/arm64"
-            is_latest: true
-          - cuda: 129
-            cuda_version: 12.9.1
-            python_version: "3.12"
-            pytorch: 2.9.1
-            axolotl_extras:
-            platforms: "linux/amd64,linux/arm64"
-          - cuda: 130
-            cuda_version: 13.0.0
-            python_version: "3.11"
-            pytorch: 2.9.1
-            axolotl_extras:
-            platforms: "linux/amd64,linux/arm64"
    runs-on: axolotl-gpu-runner
    steps:
      - name: Checkout
@@ -55,6 +45,7 @@ jobs:
        uses: docker/metadata-action@v5
        with:
          images: |
+            winglian/axolotl
            axolotlai/axolotl
          tags: |
            type=ref,event=branch
@@ -71,13 +62,14 @@ jobs:
        uses: docker/build-push-action@v5
        with:
          context: .
-          platforms: ${{ matrix.platforms }}
          build-args: |
            BASE_TAG=${{ github.ref_type == 'tag' && 'main' || github.ref_name }}-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}
            CUDA=${{ matrix.cuda }}
            PYTORCH_VERSION=${{ matrix.pytorch }}
            AXOLOTL_ARGS=${{ matrix.axolotl_args }}
            AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}
+            GIT_REF=${{ github.ref }}
+            GIT_SHA=${{ github.sha }}
          file: ./docker/Dockerfile
          push: ${{ github.event_name != 'pull_request' }}
          tags: |
@@ -93,37 +85,33 @@ jobs:
    strategy:
      matrix:
        include:
+          - cuda: 126
+            cuda_version: 12.6.3
+            python_version: "3.11"
+            pytorch: 2.6.0
+            axolotl_extras:
+          - cuda: 126
+            cuda_version: 12.6.3
+            python_version: "3.11"
+            pytorch: 2.7.1
+            axolotl_extras:
+            is_latest:
+          - cuda: 126
+            cuda_version: 12.6.3
+            python_version: "3.11"
+            pytorch: 2.7.1
+            axolotl_extras: vllm
+            is_latest: true
+          - cuda: 128
+            cuda_version: 12.8.1
+            python_version: "3.11"
+            pytorch: 2.7.1
+            axolotl_extras:
          - cuda: 128
            cuda_version: 12.8.1
            python_version: "3.11"
            pytorch: 2.8.0
            axolotl_extras:
-            platforms: "linux/amd64"
-          - cuda: 128
-            cuda_version: 12.8.1
-            python_version: "3.11"
-            pytorch: 2.9.0
-            axolotl_extras:
-            platforms: "linux/amd64,linux/arm64"
-          - cuda: 128
-            cuda_version: 12.8.1
-            python_version: "3.11"
-            pytorch: 2.9.1
-            axolotl_extras:
-            is_latest: true
-            platforms: "linux/amd64,linux/arm64"
-          - cuda: 129
-            cuda_version: 12.9.1
-            python_version: "3.12"
-            pytorch: 2.9.1
-            axolotl_extras:
-            platforms: "linux/amd64,linux/arm64"
-          - cuda: 130
-            cuda_version: 13.0.0
-            python_version: "3.11"
-            pytorch: 2.9.1
-            axolotl_extras:
-            platforms: "linux/amd64,linux/arm64"
    runs-on: axolotl-gpu-runner
    steps:
      - name: Checkout
@@ -133,6 +121,7 @@ jobs:
        uses: docker/metadata-action@v5
        with:
          images: |
+            winglian/axolotl-cloud
            axolotlai/axolotl-cloud
          tags: |
            type=ref,event=branch
@@ -148,10 +137,11 @@ jobs:
        uses: docker/build-push-action@v5
        with:
          context: .
-          platforms: ${{ matrix.platforms }}
          build-args: |
            BASE_TAG=${{ github.ref_type == 'tag' && 'main' || github.ref_name }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
            CUDA=${{ matrix.cuda }}
+            GIT_REF=${{ github.ref }}
+            GIT_SHA=${{ github.sha }}
          file: ./docker/Dockerfile-cloud
          push: ${{ github.event_name != 'pull_request' }}
          tags: |
@@ -166,16 +156,27 @@ jobs:
    strategy:
      matrix:
        include:
+          - cuda: 126
+            cuda_version: 12.6.3
+            python_version: "3.11"
+            pytorch: 2.6.0
+            axolotl_extras:
+          - cuda: 126
+            cuda_version: 12.6.3
+            python_version: "3.11"
+            pytorch: 2.7.1
+            axolotl_extras:
+            is_latest:
+          - cuda: 126
+            cuda_version: 12.6.3
+            python_version: "3.11"
+            pytorch: 2.7.1
+            axolotl_extras: vllm
+            is_latest: true
          - cuda: 128
            cuda_version: 12.8.1
            python_version: "3.11"
-            pytorch: 2.9.1
-            axolotl_extras:
-            is_latest: true
-          - cuda: 130
-            cuda_version: 13.0.0
-            python_version: "3.11"
-            pytorch: 2.9.1
+            pytorch: 2.8.0
            axolotl_extras:
            is_latest:
    runs-on: axolotl-gpu-runner
@@ -187,6 +188,7 @@ jobs:
        uses: docker/metadata-action@v5
        with:
          images: |
+            winglian/axolotl-cloud-term
            axolotlai/axolotl-cloud-term
          tags: |
            type=ref,event=branch
@@ -202,10 +204,11 @@ jobs:
        uses: docker/build-push-action@v5
        with:
          context: .
-          platforms: linux/amd64,linux/arm64
          build-args: |
            BASE_TAG=${{ github.ref_type == 'tag' && 'main' || github.ref_name }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
            CUDA=${{ matrix.cuda }}
+            GIT_REF=${{ github.ref }}
+            GIT_SHA=${{ github.sha }}
          file: ./docker/Dockerfile-cloud-no-tmux
          push: ${{ github.event_name != 'pull_request' }}
          tags: |
--- a/.github/workflows/multi-gpu-e2e.yml
+++ b/.github/workflows/multi-gpu-e2e.yml
@@ -4,8 +4,6 @@ on:
  pull_request:
    paths:
      - 'tests/e2e/multigpu/**.py'
-      - 'requirements.txt'
-      - 'setup.py'
      - 'pyproject.toml'
      - '.github/workflows/multi-gpu-e2e.yml'
      - 'src/axolotl/core/trainers/mixins/sequence_parallel.py'
@@ -19,9 +17,6 @@ concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}

-env:
-  MODAL_IMAGE_BUILDER_VERSION: "2025.06"
-
 jobs:
  test-axolotl-multigpu:
    if: ${{ ! contains(github.event.commits[0].message, '[skip e2e]') && github.repository_owner == 'axolotl-ai-cloud' && (github.event_name != 'pull_request' || !github.event.pull_request.draft) }}
@@ -29,32 +24,27 @@ jobs:
      fail-fast: false
      matrix:
        include:
+          - cuda: 126
+            cuda_version: 12.6.3
+            python_version: "3.11"
+            pytorch: 2.6.0
+            axolotl_extras:
+            num_gpus: 2
+            nightly_build: "true"
+          - cuda: 126
+            cuda_version: 12.6.3
+            python_version: "3.11"
+            pytorch: 2.7.1
+            axolotl_extras: vllm
+            num_gpus: 2
+            nightly_build: "true"
          - cuda: 128
            cuda_version: 12.8.1
            python_version: "3.11"
            pytorch: 2.8.0
            axolotl_extras: fbgemm-gpu
            num_gpus: 2
-          - cuda: 128
-            cuda_version: 12.8.1
-            python_version: "3.11"
-            pytorch: 2.9.1
-            axolotl_extras: "fbgemm-gpu"
-            num_gpus: 2
-          - cuda: 129
-            cuda_version: 12.9.1
-            python_version: "3.12"
-            pytorch: 2.9.1
-            axolotl_extras: "fbgemm-gpu"
-            num_gpus: 2
-            dockerfile: "Dockerfile-uv.jinja"
-          - cuda: 130
-            cuda_version: 13.0.0
-            python_version: "3.11"
-            pytorch: 2.9.1
-            axolotl_extras:
-#            axolotl_extras: fbgemm-gpu
-            num_gpus: 2
+            nightly_build: "true"
    runs-on: [self-hosted, modal]
    timeout-minutes: 120
    steps:
@@ -64,20 +54,24 @@ jobs:
        uses: actions/setup-python@v5
        with:
          python-version: "3.11"
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
      - name: Install Modal
        run: |
          python -m pip install --upgrade pip
-          pip install modal==1.3.0.post1 jinja2
+          pip install modal==1.0.2 jinja2 protobuf
      - name: Update env vars
        run: |
-          echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
+          echo "BASE_TAG=${{ github.ref_name }}-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
          echo "PYTORCH_VERSION=${{ matrix.pytorch}}" >> $GITHUB_ENV
          echo "AXOLOTL_ARGS=${{ matrix.axolotl_args}}" >> $GITHUB_ENV
          echo "AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}" >> $GITHUB_ENV
          echo "CUDA=${{ matrix.cuda }}" >> $GITHUB_ENV
          echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV
+          echo "NIGHTLY_BUILD=${{ matrix.nightly_build }}" >> $GITHUB_ENV
          echo "CODECOV_TOKEN=${{ secrets.CODECOV_TOKEN }}" >> $GITHUB_ENV
-          echo "E2E_DOCKERFILE=${{ matrix.dockerfile || 'Dockerfile.jinja'}}" >> $GITHUB_ENV
      - name: Run tests job on Modal
        run: |
          modal run -m cicd.multigpu
--- a/.github/workflows/nightlies.yml
+++ b/.github/workflows/nightlies.yml
@@ -12,15 +12,15 @@ jobs:
      fail-fast: false
      matrix:
        include:
-          - cuda: 128
-            cuda_version: 12.8.1
+          - cuda: 126
+            cuda_version: 12.6.3
            python_version: "3.11"
-            pytorch: 2.8.0
+            pytorch: 2.6.0
            axolotl_extras:
-          - cuda: 128
-            cuda_version: 12.8.1
+          - cuda: 126
+            cuda_version: 12.6.3
            python_version: "3.11"
-            pytorch: 2.9.1
+            pytorch: 2.7.1
            axolotl_extras:
    runs-on: axolotl-gpu-runner
    steps:
@@ -31,6 +31,7 @@ jobs:
        uses: docker/metadata-action@v5
        with:
          images: |
+            winglian/axolotl
            axolotlai/axolotl
          tags: |
            type=raw,value={{ branch }}-{{ date 'YYYYMMDD' }}
@@ -51,6 +52,8 @@ jobs:
            CUDA=${{ matrix.cuda }}
            PYTORCH_VERSION=${{ matrix.pytorch }}
            AXOLOTL_ARGS=${{ matrix.axolotl_args }}
+            GIT_REF=${{ github.ref }}
+            GIT_SHA=${{ github.sha }}
          file: ./docker/Dockerfile
          push: ${{ github.event_name != 'pull_request' }}
          tags: |
@@ -64,15 +67,15 @@ jobs:
    strategy:
      matrix:
        include:
-          - cuda: 128
-            cuda_version: 12.8.1
+          - cuda: 126
+            cuda_version: 12.6.3
            python_version: "3.11"
-            pytorch: 2.8.0
+            pytorch: 2.6.0
            axolotl_extras:
-          - cuda: 128
-            cuda_version: 12.8.1
+          - cuda: 126
+            cuda_version: 12.6.3
            python_version: "3.11"
-            pytorch: 2.9.1
+            pytorch: 2.7.1
            axolotl_extras:
    runs-on: axolotl-gpu-runner
    steps:
@@ -83,6 +86,7 @@ jobs:
        uses: docker/metadata-action@v5
        with:
          images: |
+            winglian/axolotl-cloud
            axolotlai/axolotl-cloud
          tags: |
            type=raw,value={{ branch }}-{{ date 'YYYYMMDD' }}
@@ -100,6 +104,8 @@ jobs:
          build-args: |
            BASE_TAG=${{ github.ref_name }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
            CUDA=${{ matrix.cuda }}
+            GIT_REF=${{ github.ref }}
+            GIT_SHA=${{ github.sha }}
          file: ./docker/Dockerfile-cloud
          push: ${{ github.event_name != 'pull_request' }}
          tags: |
--- a/.github/workflows/precommit-autoupdate.yml
+++ b/.github/workflows/precommit-autoupdate.yml
@@ -2,7 +2,7 @@ name: Pre-commit auto-update

 on:
  schedule:
-    - cron: '0 0 1 * *'  # Run monthly
+    - cron: '0 0 * * 0'  # Run weekly
  workflow_dispatch:  # Manual kickoff

 jobs:
@@ -18,10 +18,15 @@ jobs:
        with:
          python-version: '3.11'

+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
+
      - name: Update pre-commit hooks
        id: update
        run: |
-          pip install pre-commit
+          uv pip install --system pre-commit
          pre-commit autoupdate
          if [[ -n $(git status --porcelain) ]]; then
            echo "changes=true" >> $GITHUB_OUTPUT
--- a/.github/workflows/preview-docs.yml
+++ b/.github/workflows/preview-docs.yml
@@ -11,7 +11,6 @@ on:
      - '_quarto.yml'
      - docs/scripts/generate_config_docs.py
      - src/axolotl/utils/schemas/**.py
-      - .github/workflows/preview-docs.yml

 permissions:
  checks: write
@@ -28,10 +27,6 @@ jobs:
    runs-on: ubuntu-latest
    if: ${{ !github.event.pull_request.draft }}
    steps:
-      - name: cleanup node
-        run: |
-          sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL
-
      - name: Check out repository
        uses: actions/checkout@v4
        with:
@@ -45,10 +40,15 @@ jobs:
        with:
          python-version: '3.11'

+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
+
      - name: Install dependencies
        run: |
-          python3 -m pip install jupyter quartodoc
-          python3 -m pip install -e .
+          uv pip install --system jupyter quartodoc
+          uv pip install --system -e .

      - name: Build autodoc
        run: quartodoc build
--- a/.github/workflows/pypi.yml
+++ b/.github/workflows/pypi.yml
@@ -38,23 +38,24 @@ jobs:
        with:
          python-version: "3.11"

+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
+
      - name: Install dependencies
        run: |
-          pip3 install wheel packaging==26.0
-          pip3 install --no-build-isolation -e .
-          pip3 install -r requirements-dev.txt -r requirements-tests.txt
+          uv pip install --system wheel packaging==23.2
+          uv pip install --system --no-build-isolation -e ".[dev]"

      - name: Extract tag name
        id: tag
-        run: echo ::set-output name=TAG_NAME::$(echo $GITHUB_REF | cut -d / -f 3)
+        run: echo "TAG_NAME=$(echo "$GITHUB_REF" | cut -d / -f 3)" >> "$GITHUB_OUTPUT"

-      - name: Update version in VERSION file
+      - name: Build package
        run: |
-          echo "${{ steps.tag.outputs.TAG_NAME }}" | sed 's/^v//' > VERSION
-
-      - name: Build a source dist
-        run: |
-          python setup.py sdist
+          uv pip install --system build
+          python -m build

      - name: Publish package distributions to PyPI
        uses: pypa/gh-action-pypi-publish@release/v1
--- a/.github/workflows/tests-nightly.yml
+++ b/.github/workflows/tests-nightly.yml
@@ -13,7 +13,6 @@ jobs:
      - uses: actions/setup-python@v5
        with:
          python-version: "3.11"
-          cache: 'pip' # caching pip dependencies
      - uses: pre-commit/action@v3.0.1
        env:
          SKIP: no-commit-to-branch
@@ -26,7 +25,7 @@ jobs:
      max-parallel: 2
      matrix:
        python_version: ["3.11"]
-        pytorch_version: ["2.8.0", "2.9.0", "2.9.1"]
+        pytorch_version: ["2.6.0", "2.7.0"]
    timeout-minutes: 20

    steps:
@@ -43,32 +42,30 @@ jobs:
        uses: actions/setup-python@v5
        with:
          python-version: ${{ matrix.python_version }}
-          cache: 'pip' # caching pip dependencies

-      - name: upgrade pip
-        run: |
-          pip3 install --upgrade pip
-          pip3 install --upgrade packaging==26.0 setuptools==75.8.0 wheel
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"

      - name: Install PyTorch
        run: |
-          pip3 install torch==${{ matrix.pytorch_version }} torchvision
+          uv pip install --system torch==${{ matrix.pytorch_version }} torchvision

-      - name: Update requirements.txt
+      - name: Update pyproject.toml for nightly builds
        run: |
-          sed -i 's#^transformers.*#transformers @ git+https://github.com/huggingface/transformers.git@main#' requirements.txt
-          sed -i 's#^peft.*#peft @ git+https://github.com/huggingface/peft.git@main#' requirements.txt
-          sed -i 's#^accelerate.*#accelerate @ git+https://github.com/huggingface/accelerate.git@main#' requirements.txt
-          sed -i 's#^trl.*#trl @ git+https://github.com/huggingface/trl.git@main#' requirements.txt
-          sed -i 's#^datasets.*#datasets @ git+https://github.com/huggingface/datasets.git@main#' requirements.txt
+          sed -i 's#"transformers==.*"#"transformers @ git+https://github.com/huggingface/transformers.git@main"#' pyproject.toml
+          sed -i 's#"peft==.*"#"peft @ git+https://github.com/huggingface/peft.git@main"#' pyproject.toml
+          sed -i 's#"accelerate==.*"#"accelerate @ git+https://github.com/huggingface/accelerate.git@main"#' pyproject.toml
+          sed -i 's#"trl==.*"#"trl @ git+https://github.com/huggingface/trl.git@main"#' pyproject.toml
+          sed -i 's#"datasets==.*"#"datasets @ git+https://github.com/huggingface/datasets.git@main"#' pyproject.toml

      - name: Install dependencies
        run: |
-          pip3 show torch
-          pip3 install --no-build-isolation -U -e .
+          uv pip show --system torch
+          uv pip install --system --no-build-isolation -e ".[dev]"
          python scripts/unsloth_install.py | sh
          python scripts/cutcrossentropy_install.py | sh
-          pip3 install -r requirements-dev.txt -r requirements-tests.txt

      - name: Make sure PyTorch version wasn't clobbered
        run: |
@@ -84,9 +81,6 @@ jobs:
          pytest -v --durations=10 tests/patched/
          pytest -v --durations=10 tests/cli/

-      - name: cleanup pip cache
-        run: |
-          find "$(pip cache dir)/http-v2" -type f -mtime +14 -exec rm {} \;

  docker-e2e-tests:
    if: github.repository_owner == 'axolotl-ai-cloud'
@@ -99,17 +93,17 @@ jobs:
      fail-fast: false
      matrix:
        include:
-          - cuda: 128
-            cuda_version: 12.8.1
+          - cuda: 126
+            cuda_version: 12.6.3
            python_version: "3.11"
-            pytorch: 2.8.0
+            pytorch: 2.6.0
            num_gpus: 1
            axolotl_extras:
            nightly_build: "true"
-          - cuda: 128
-            cuda_version: 12.8.1
+          - cuda: 126
+            cuda_version: 12.6.3
            python_version: "3.11"
-            pytorch: 2.9.1
+            pytorch: 2.7.1
            num_gpus: 1
            axolotl_extras:
            nightly_build: "true"
@@ -120,13 +114,16 @@ jobs:
        uses: actions/setup-python@v5
        with:
          python-version: "3.11"
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
      - name: Install Modal
        run: |
-          python -m pip install --upgrade pip
-          pip install modal==1.3.0.post1 jinja2
+          uv pip install --system modal==1.0.2 jinja2
      - name: Update env vars
        run: |
-          echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
+          echo "BASE_TAG=main-base-uv-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
          echo "PYTORCH_VERSION=${{ matrix.pytorch}}" >> $GITHUB_ENV
          echo "AXOLOTL_ARGS=${{ matrix.axolotl_args}}" >> $GITHUB_ENV
          echo "AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}" >> $GITHUB_ENV
@@ -136,7 +133,7 @@ jobs:
          echo "CODECOV_TOKEN=${{ secrets.CODECOV_TOKEN }}" >> $GITHUB_ENV
      - name: Run tests job on Modal
        run: |
-          modal run cicd.e2e_tests
+          modal run -m cicd.e2e_tests
  docker-e2e-multigpu-tests:
    if: github.repository_owner == 'axolotl-ai-cloud'
    # this job needs to be run on self-hosted GPU runners...
@@ -148,10 +145,10 @@ jobs:
      fail-fast: false
      matrix:
        include:
-          - cuda: 128
-            cuda_version: 12.8.1
+          - cuda: 126
+            cuda_version: 12.6.3
            python_version: "3.11"
-            pytorch: 2.9.1
+            pytorch: 2.7.1
            num_gpus: 2
            axolotl_extras:
            nightly_build: "true"
@@ -162,13 +159,16 @@ jobs:
        uses: actions/setup-python@v5
        with:
          python-version: "3.11"
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
      - name: Install Modal
        run: |
-          python -m pip install --upgrade pip
-          pip install modal==1.3.0.post1 jinja2
+          uv pip install --system modal==1.0.2 jinja2
      - name: Update env vars
        run: |
-          echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
+          echo "BASE_TAG=main-base-uv-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
          echo "PYTORCH_VERSION=${{ matrix.pytorch}}" >> $GITHUB_ENV
          echo "AXOLOTL_ARGS=${{ matrix.axolotl_args}}" >> $GITHUB_ENV
          echo "AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}" >> $GITHUB_ENV
--- a/.github/workflows/tests.yml
+++ b/.github/workflows/tests.yml
@@ -7,18 +7,16 @@ on:
      - "main"
    paths:
      - '**.py'
-      - 'requirements.txt'
+      - 'pyproject.toml'
      - '.github/workflows/*.yml'
-      - 'requirements-tests.txt'
      - 'cicd/cicd.sh'
      - 'cicd/Dockerfile.jinja'
  pull_request:
      types: [opened, synchronize, reopened, ready_for_review]
      paths:
       - '**.py'
-       - 'requirements.txt'
+       - 'pyproject.toml'
       - '.github/workflows/*.yml'
-       - 'requirements-tests.txt'
       - 'cicd/cicd.sh'
       - 'cicd/Dockerfile.jinja'
  workflow_dispatch:
@@ -41,7 +39,6 @@ jobs:
      - uses: actions/setup-python@v5
        with:
          python-version: "3.11"
-          cache: 'pip' # caching pip dependencies
      - uses: pre-commit/action@v3.0.1
        env:
          SKIP: no-commit-to-branch
@@ -54,56 +51,43 @@ jobs:
    strategy:
      fail-fast: false
      matrix:
-        python_version: ["3.11", "3.12"]
-        pytorch_version: ["2.8.0", "2.9.0", "2.9.1"]
-        exclude:
-          - python_version: "3.12"
-            pytorch_version: "2.8.0"
-          - python_version: "3.12"
-            pytorch_version: "2.9.0"
+        python_version: ["3.11"]
+        pytorch_version: ["2.6.0", "2.7.1", "2.8.0"]
    timeout-minutes: 20

    steps:
-      - name: cleanup node
-        run: |
-          sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL
-
      - name: Check out repository code
        uses: actions/checkout@v4

      - name: Restore Cache from S3
        id: hf-cache-restore-s3
        run: |
-          mkdir -p ~/.cache/huggingface/hub
-          curl -L https://d1dttdx32dkk5p.cloudfront.net/hf-cache.tar.zst | tar -xpf - -C ~/.cache/huggingface/hub/  --use-compress-program unzstd --strip-components=1
-          ls -ltr ~/.cache/huggingface/hub/
+          mkdir -p /home/runner/.cache/huggingface/hub
+          curl -L https://d1dttdx32dkk5p.cloudfront.net/hf-cache.tar.zst | tar -xf - -C /home/runner/.cache/huggingface/hub/  --use-compress-program unzstd

      - name: Setup Python
        uses: actions/setup-python@v5
        with:
          python-version: ${{ matrix.python_version }}
-          cache: 'pip' # caching pip dependencies

-      - name: upgrade pip
-        run: |
-          pip3 install --upgrade pip
-          pip3 install --upgrade packaging==26.0 setuptools==75.8.0 wheel
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"

      - name: Install PyTorch
        run: |
-          pip3 install --no-cache-dir torch==${{ matrix.pytorch_version }} torchvision
+          uv pip install --system torch==${{ matrix.pytorch_version }} torchvision

      - name: Install dependencies
        run: |
-          pip3 show torch
-          pip3 install --no-cache-dir --no-build-isolation -U -e .
-          python scripts/unsloth_install.py | sh
-          python scripts/cutcrossentropy_install.py | sh
-          pip3 install -r requirements-dev.txt -r requirements-tests.txt
-
-      - name: cleanup pip cache
-        run: |
-          find "$(pip cache dir)/http-v2" -type f -mtime +14 -exec rm {} \;
+          uv pip show --system torch
+          uv pip install --system wheel
+          printf "torch==${{ matrix.pytorch_version }}\n" > torch-constraints.txt
+          uv pip install --system --no-cache-dir --no-build-isolation -e ".[dev]" --constraints torch-constraints.txt
+          set -o pipefail
+          python scripts/unsloth_install.py | bash
+          python scripts/cutcrossentropy_install.py | bash

      - name: Make sure PyTorch version wasn't clobbered
        run: |
@@ -115,24 +99,14 @@ jobs:

      - name: Pre-Download dataset fixture
        run: |
-          hf download --repo-type=dataset axolotl-ai-internal/axolotl-oss-dataset-fixtures
-
-      - name: Show HF cache
-        run: hf cache ls
+          huggingface-cli download --repo-type=dataset axolotl-ai-internal/axolotl-oss-dataset-fixtures

      - name: Run tests
        run: |
-          df -h
-          pytest -v --durations=10 -n4 --dist loadfile --ignore=tests/e2e/ --ignore=tests/patched/ --ignore=tests/cli/ --ignore=tests/monkeypatch/ tests/ --cov=axolotl --cov-report=xml
-          df -h
-          pytest -v --durations=10 tests/monkeypatch/ --cov=axolotl --cov-append --cov-report=xml
-          df -h
-          pytest -v --durations=10 tests/patched/ --cov=axolotl --cov-append --cov-report=xml
-          df -h
-          pytest -v --durations=10 tests/cli/ --cov=axolotl --cov-append --cov-report=xml
-
-      - name: Show HF cache
-        run: hf cache ls
+          python -m pytest -v --durations=10 -n 8 --dist loadfile --cov=axolotl --cov-report=xml --ignore=tests/e2e/ --ignore=tests/patched/ --ignore=tests/cli/ --ignore=tests/monkeypatch/ tests/
+          python -m pytest -v --durations=10 -n 8 --cov=axolotl --cov-append --cov-report=xml tests/monkeypatch/
+          python -m pytest -v --durations=10 -n 8 --cov=axolotl --cov-append --cov-report=xml tests/patched/
+          python -m pytest -v --durations=10 -n 8 --cov=axolotl --cov-append --cov-report=xml tests/cli/

      - name: Upload coverage to Codecov
        uses: codecov/codecov-action@v5
@@ -142,6 +116,7 @@ jobs:
          flags: unittests,pytorch-${{ matrix.pytorch_version }}
          fail_ci_if_error: false

+
  pytest-sdist:
    name: PyTest from Source Dist
    runs-on: ubuntu-latest
@@ -149,57 +124,44 @@ jobs:
    strategy:
      fail-fast: false
      matrix:
-        python_version: ["3.11", "3.12"]
-        pytorch_version: ["2.8.0", "2.9.0", "2.9.1"]
-        exclude:
-          - python_version: "3.12"
-            pytorch_version: "2.8.0"
-          - python_version: "3.12"
-            pytorch_version: "2.9.0"
+        python_version: ["3.11"]
+        pytorch_version: ["2.6.0", "2.7.1", "2.8.0"]
    timeout-minutes: 20

    steps:
-      - name: cleanup node
-        run: |
-          sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL
-
      - name: Check out repository code
        uses: actions/checkout@v4

      - name: Restore Cache from S3
        id: hf-cache-restore-s3
        run: |
-          mkdir -p ~/.cache/huggingface/hub
-          curl -L https://d1dttdx32dkk5p.cloudfront.net/hf-cache.tar.zst | tar -xpf - -C ~/.cache/huggingface/hub/  --use-compress-program unzstd --strip-components=1
-          ls -ltr ~/.cache/huggingface/hub/
+          mkdir -p /home/runner/.cache/huggingface/hub
+          curl -L https://d1dttdx32dkk5p.cloudfront.net/hf-cache.tar.zst | tar -xf - -C /home/runner/.cache/huggingface/hub/  --use-compress-program unzstd

      - name: Setup Python
        uses: actions/setup-python@v5
        with:
          python-version: ${{ matrix.python_version }}
-          cache: 'pip' # caching pip dependencies

-      - name: upgrade pip
-        run: |
-          pip3 install --upgrade pip
-          pip3 install --upgrade packaging==26.0 setuptools==75.8.0 setuptools_scm build wheel psutil
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"

      - name: Install PyTorch
        run: |
-          pip3 install --no-cache-dir torch==${{ matrix.pytorch_version }} torchvision
+          uv pip install --system torch==${{ matrix.pytorch_version }} torchvision

      - name: Install dependencies
        run: |
-          pip3 show torch
-          python -m build --no-isolation --sdist
-          pip3 install --no-cache-dir --no-build-isolation dist/axolotl*.tar.gz
+          uv pip show --system torch
+          uv pip install --system wheel build setuptools_scm
+          python -m build --sdist
+          printf "torch==${{ matrix.pytorch_version }}\n" > torch-constraints.txt
+          tarball_path=$(echo dist/axolotl*.tar.gz)
+          uv pip install --no-cache-dir --no-build-isolation --system "${tarball_path}[dev]" --constraints torch-constraints.txt
          python scripts/unsloth_install.py | sh
          python scripts/cutcrossentropy_install.py | sh
-          pip3 install -r requirements-dev.txt -r requirements-tests.txt
-
-      - name: cleanup pip cache
-        run: |
-          find "$(pip cache dir)/http-v2" -type f -mtime +14 -exec rm {} \;

      - name: Make sure PyTorch version wasn't clobbered
        run: |
@@ -210,19 +172,16 @@ jobs:
          axolotl --help

      - name: Show HF cache
-        run: hf cache ls
+        run: huggingface-cli scan-cache

      - name: Run tests
        run: |
-          pytest -v --durations=10 -n4 --dist loadfile --ignore=tests/e2e/ --ignore=tests/patched/ --ignore=tests/cli/ --ignore=tests/monkeypatch/ tests/ --cov=axolotl --cov-report=xml
-          pytest -v --durations=10 tests/monkeypatch/ --cov=axolotl --cov-append --cov-report=xml
-          pytest -v --durations=10 tests/cli/
-
-      - name: Show HF cache
-        run: hf cache ls
+          python -m pytest -v --durations=10 -n 8 --dist loadfile --cov=axolotl --cov-report=xml --ignore=tests/e2e/ --ignore=tests/patched/ --ignore=tests/cli/ --ignore=tests/monkeypatch/ tests/
+          python -m pytest -v --durations=10 -n 8 --cov=axolotl --cov-append --cov-report=xml tests/monkeypatch/
+          python -m pytest -v --durations=10 -n 8 tests/cli/

  gate-skip-e2e:
-    needs: [pre-commit]
+    needs: [pre-commit, pytest, pytest-sdist]
    runs-on: ubuntu-latest
    outputs:
      skip: ${{ steps.compute.outputs.skip }}
@@ -258,19 +217,25 @@ jobs:
    # this job needs to be run on self-hosted GPU runners...
    runs-on: [self-hosted, modal]
    timeout-minutes: 120
-    needs: [pre-commit, pytest]
+    needs: [pre-commit, pytest, pytest-sdist, gate-skip-e2e]

    strategy:
      fail-fast: false
      matrix:
        include:
-          - cuda: 129
-            cuda_version: 12.9.1
-            python_version: "3.12"
-            pytorch: 2.9.1
+          - cuda: 126
+            cuda_version: 12.6.3
+            python_version: "3.11"
+            pytorch: 2.7.1
            num_gpus: 1
            axolotl_extras:
-            dockerfile: "Dockerfile-uv.jinja"
+          - cuda: 126
+            cuda_version: 12.6.3
+            python_version: "3.11"
+            pytorch: 2.7.1
+            num_gpus: 1
+            axolotl_extras:
+            dockerfile: "Dockerfile.jinja"
    steps:
      - name: Checkout
        uses: actions/checkout@v4
@@ -278,13 +243,17 @@ jobs:
        uses: actions/setup-python@v5
        with:
          python-version: "3.11"
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
      - name: Install Modal
        run: |
          python -m pip install --upgrade pip
-          pip install modal==1.3.0.post1 jinja2
+          pip install modal==1.0.2 jinja2 protobuf
      - name: Update env vars
        run: |
-          echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
+          echo "BASE_TAG=${{ github.ref_name }}-base-uv-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
          echo "PYTORCH_VERSION=${{ matrix.pytorch}}" >> $GITHUB_ENV
          echo "AXOLOTL_ARGS=${{ matrix.axolotl_args}}" >> $GITHUB_ENV
          echo "AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}" >> $GITHUB_ENV
@@ -313,6 +282,18 @@ jobs:
      fail-fast: false
      matrix:
        include:
+          - cuda: 126
+            cuda_version: 12.6.3
+            python_version: "3.11"
+            pytorch: 2.6.0
+            num_gpus: 1
+            axolotl_extras:
+          - cuda: 128
+            cuda_version: 12.8.1
+            python_version: "3.11"
+            pytorch: 2.7.1
+            num_gpus: 1
+            axolotl_extras:
          - cuda: 128
            cuda_version: 12.8.1
            python_version: "3.11"
@@ -320,18 +301,6 @@ jobs:
            num_gpus: 1
            gpu_type: "B200"
            axolotl_extras: fbgemm-gpu
-          - cuda: 128
-            cuda_version: 12.8.1
-            python_version: "3.11"
-            pytorch: 2.9.1
-            num_gpus: 1
-            axolotl_extras:
-          - cuda: 130
-            cuda_version: 13.0.0
-            python_version: "3.11"
-            pytorch: 2.9.1
-            num_gpus: 1
-            axolotl_extras:
    steps:
      - name: Checkout
        uses: actions/checkout@v4
@@ -339,13 +308,17 @@ jobs:
        uses: actions/setup-python@v5
        with:
          python-version: "3.11"
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
      - name: Install Modal
        run: |
          python -m pip install --upgrade pip
-          pip install modal==1.3.0.post1 jinja2
+          pip install modal==1.0.2 jinja2 protobuf
      - name: Update env vars
        run: |
-          echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
+          echo "BASE_TAG=${{ github.ref_name }}-base-uv-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
          echo "PYTORCH_VERSION=${{ matrix.pytorch}}" >> $GITHUB_ENV
          echo "AXOLOTL_ARGS=${{ matrix.axolotl_args}}" >> $GITHUB_ENV
          echo "AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}" >> $GITHUB_ENV
@@ -369,10 +342,10 @@ jobs:
      fail-fast: false
      matrix:
        include:
-          - cuda: 129
-            cuda_version: 12.9.1
-            python_version: "3.12"
-            pytorch: 2.9.1
+          - cuda: 126
+            cuda_version: 12.6.3
+            python_version: "3.11"
+            pytorch: 2.7.1
            num_gpus: 1
            axolotl_extras:
    steps:
@@ -382,13 +355,17 @@ jobs:
        uses: actions/setup-python@v5
        with:
          python-version: "3.11"
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
      - name: Install Modal
        run: |
          python -m pip install --upgrade pip
-          pip install modal==1.3.0.post1 jinja2
+          pip install modal==1.0.2 jinja2 protobuf
      - name: Update env vars
        run: |
-          echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
+          echo "BASE_TAG=${{ github.ref_name }}-base-uv-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
          echo "PYTORCH_VERSION=${{ matrix.pytorch}}" >> $GITHUB_ENV
          echo "AXOLOTL_ARGS=${{ matrix.axolotl_args}}" >> $GITHUB_ENV
          echo "AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}" >> $GITHUB_ENV
--- a/.gitignore
+++ b/.gitignore
@@ -191,5 +191,5 @@ out/
 # vim
 *.swp

-# scm auto-versioning
+# setuptools-scm generated version file
 src/axolotl/_version.py
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -11,13 +11,13 @@ repos:
    -   id: no-commit-to-branch
        args: ['--branch', 'main']
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.14.10
+    rev: v0.12.12
    hooks:
    -   id: ruff
        args: [--fix]
    -   id: ruff-format
 -   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.19.1
+    rev: v1.17.1
    hooks:
    - id: mypy
      additional_dependencies:
@@ -26,7 +26,7 @@ repos:
            'pydantic>=2.5.3',
        ]
 -   repo: https://github.com/PyCQA/bandit
-    rev: 1.9.2
+    rev: 1.8.6
    hooks:
    -   id: bandit
        args: [
--- a/.runpod/Dockerfile
+++ b/.runpod/Dockerfile
@@ -1,16 +1,14 @@
 FROM axolotlai/axolotl-cloud:main-py3.11-cu124-2.6.0

 COPY .runpod/requirements.txt /requirements.txt
-RUN --mount=type=cache,target=/root/.cache/pip \
-    python3 -m pip install --upgrade pip && \
-    python3 -m pip install --upgrade -r /requirements.txt
+RUN curl -LsSf https://astral.sh/uv/install.sh | sh && \
+    /root/.local/bin/uv pip install --system -r /requirements.txt

 # Environment settings
 ARG BASE_VOLUME="/runpod-volume"
 ENV BASE_VOLUME=$BASE_VOLUME
 ENV HF_DATASETS_CACHE="${BASE_VOLUME}/huggingface-cache/datasets"
 ENV HUGGINGFACE_HUB_CACHE="${BASE_VOLUME}/huggingface-cache/hub"
-ENV HF_HUB_CACHE="${BASE_VOLUME}/huggingface-cache/hub"
 ENV TRANSFORMERS_CACHE="${BASE_VOLUME}/huggingface-cache/hub"

 COPY .runpod/src /src
--- a/.runpod/README.md
+++ b/.runpod/README.md
@@ -123,7 +123,7 @@ datasets:
 | --------------------------------- | -------------------------- | ----------------------------------- |
 | `dataset_prepared_path`           | `"data/last_run_prepared"` | Path for prepared dataset           |
 | `push_dataset_to_hub`             | `""`                       | Push dataset to HF hub              |
-| `dataset_num_proc`                | `4`                        | Number of preprocessing processes   |
+| `dataset_processes`               | `4`                        | Number of preprocessing processes   |
 | `dataset_keep_in_memory`          | `false`                    | Keep dataset in memory              |
 | `shuffle_merged_datasets`         | `true`                     | Shuffle merged datasets             |
 | `shuffle_before_merging_datasets` | `false`                    | Shuffle each dataset before merging |
--- a/.runpod/src/config/config.yaml
+++ b/.runpod/src/config/config.yaml
@@ -39,6 +39,7 @@
 #     type: # linear | dynamic
 #     factor: # float

+
 # # Whether you are training a 4-bit GPTQ quantized model
 # gptq: true
 # gptq_groupsize: 128 # group size
@@ -106,7 +107,7 @@
 # push_dataset_to_hub: # repo path
 # # The maximum number of processes to use while preprocessing your input dataset. This defaults to `os.cpu_count()`
 # # if not set.
-# dataset_num_proc: # defaults to os.cpu_count() if not set
+# dataset_processes: # defaults to os.cpu_count() if not set
 # # push checkpoints to hub
 # hub_model_id: # repo path to push finetuned model
 # # how to push checkpoints to hub
@@ -223,6 +224,9 @@
 # eval_table_size: # Approximate number of predictions sent to wandb depending on batch size. Enabled above 0. Default is 0
 # eval_table_max_new_tokens: # Total number of tokens generated for predictions sent to wandb. Default is 128

+# # Save model as safetensors (require safetensors package)
+# save_safetensors:
+
 # # Whether to mask out or include the human's prompt from the training labels
 # train_on_inputs: false
 # # Group similarly sized data to minimize padding.
@@ -348,6 +352,8 @@
 # # Allow overwrite yml config using from cli
 # strict:

+
+
 base_model: ${BASE_MODEL}
 base_model_ignore_patterns: ${BASE_MODEL_IGNORE_PATTERNS}
 base_model_config: ${BASE_MODEL_CONFIG}
@@ -406,7 +412,7 @@ chat_template_jinja: ${CHAT_TEMPLATE_JINJA}
 default_system_message: ${DEFAULT_SYSTEM_MESSAGE}
 dataset_prepared_path: ${DATASET_PREPARED_PATH}
 push_dataset_to_hub: ${PUSH_DATASET_TO_HUB}
-dataset_num_proc: ${DATASET_NUM_PROC}
+dataset_processes: ${DATASET_PROCESSES}
 dataset_keep_in_memory: ${DATASET_KEEP_IN_MEMORY}
 hub_model_id: ${HUB_MODEL_ID}
 hub_strategy: ${HUB_STRATEGY}
@@ -506,6 +512,7 @@ profiler_steps: ${PROFILER_STEPS}
 loss_watchdog_threshold: ${LOSS_WATCHDOG_THRESHOLD}
 loss_watchdog_patience: ${LOSS_WATCHDOG_PATIENCE}

+save_safetensors: ${SAVE_SAFETENSORS}
 train_on_inputs: ${TRAIN_ON_INPUTS}
 group_by_length: ${GROUP_BY_LENGTH}
 gradient_checkpointing: ${GRADIENT_CHECKPOINTING}
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -1,6 +1,5 @@
-include requirements.txt
+include pyproject.toml
 include README.md
 include LICENSE
-include src/setuptools_axolotl_dynamic_dependencies.py
 include src/axolotl/utils/chat_templates/templates/*.jinja
-recursive-include axolotl *.py
+recursive-include src/axolotl *.py
--- a/README.md
+++ b/README.md
@@ -29,25 +29,21 @@

 ## 🎉 Latest Updates

- 2025/12: Axolotl now includes support for [Kimi-Linear](https://docs.axolotl.ai/docs/models/kimi-linear.html), [Plano-Orchestrator](https://docs.axolotl.ai/docs/models/plano.html), [MiMo](https://docs.axolotl.ai/docs/models/mimo.html), [InternVL 3.5](https://docs.axolotl.ai/docs/models/internvl3_5.html), [Olmo3](https://docs.axolotl.ai/docs/models/olmo3.html), [Trinity](https://docs.axolotl.ai/docs/models/trinity.html), and [Ministral3](https://docs.axolotl.ai/docs/models/ministral3.html).
- 2025/10: New model support has been added in Axolotl for: [Qwen3 Next](https://docs.axolotl.ai/docs/models/qwen3-next.html), [Qwen2.5-vl, Qwen3-vl](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/qwen2_5-vl), [Qwen3, Qwen3MoE](https://docs.axolotl.ai/docs/models/qwen3.html), [Granite 4](https://docs.axolotl.ai/docs/models/granite4.html), [HunYuan](https://docs.axolotl.ai/docs/models/hunyuan.html), [Magistral 2509](https://docs.axolotl.ai/docs/models/magistral/vision.html), [Apertus](https://docs.axolotl.ai/docs/models/apertus.html), and [Seed-OSS](https://docs.axolotl.ai/docs/models/seed-oss.html).
- 2025/09: Axolotl now has text diffusion training. Read more [here](https://github.com/axolotl-ai-cloud/axolotl/tree/main/src/axolotl/integrations/diffusion).
- 2025/08: QAT has been updated to include NVFP4 support. See [PR](https://github.com/axolotl-ai-cloud/axolotl/pull/3107).
 - 2025/07:
  - ND Parallelism support has been added into Axolotl. Compose Context Parallelism (CP), Tensor Parallelism (TP), and Fully Sharded Data Parallelism (FSDP) within a single node and across multiple nodes. Check out the [blog post](https://huggingface.co/blog/accelerate-nd-parallel) for more info.
-  - Axolotl adds more models: [GPT-OSS](https://docs.axolotl.ai/docs/models/gpt-oss.html), [Gemma 3n](https://docs.axolotl.ai/docs/models/gemma3n.html), [Liquid Foundation Model 2 (LFM2)](https://docs.axolotl.ai/docs/models/LiquidAI.html), and [Arcee Foundation Models (AFM)](https://docs.axolotl.ai/docs/models/arcee.html).
+  - Axolotl adds more models: [GPT-OSS](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/gpt-oss), [Gemma 3n](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/gemma3n), [Liquid Foundation Model 2 (LFM2)](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/lfm2), and [Arcee Foundation Models (AFM)](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/afm).
  - FP8 finetuning with fp8 gather op is now possible in Axolotl via `torchao`. Get started [here](https://docs.axolotl.ai/docs/mixed_precision.html#sec-fp8)!
-  - [Voxtral](https://docs.axolotl.ai/docs/models/voxtral.html), [Magistral 1.1](https://docs.axolotl.ai/docs/models/magistral.html), and [Devstral](https://docs.axolotl.ai/docs/models/devstral.html) with mistral-common tokenizer support has been integrated in Axolotl!
+  - [Voxtral](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/voxtral), [Magistral 1.1](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/magistral), and [Devstral](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/devstral) with mistral-common tokenizer support has been integrated in Axolotl!
  - TiledMLP support for single-GPU to multi-GPU training with DDP, DeepSpeed and FSDP support has been added to support Arctic Long Sequence Training. (ALST). See [examples](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/alst) for using ALST with Axolotl!
 - 2025/05: Quantization Aware Training (QAT) support has been added to Axolotl. Explore the [docs](https://docs.axolotl.ai/docs/qat.html) to learn more!
+- 2025/03: Axolotl has implemented Sequence Parallelism (SP) support. Read the [blog](https://huggingface.co/blog/axolotl-ai-co/long-context-with-sequence-parallelism-in-axolotl) and [docs](https://docs.axolotl.ai/docs/sequence_parallelism.html) to learn how to scale your context length when fine-tuning.

 <details>

 <summary>Expand older updates</summary>

- 2025/03: Axolotl has implemented Sequence Parallelism (SP) support. Read the [blog](https://huggingface.co/blog/axolotl-ai-co/long-context-with-sequence-parallelism-in-axolotl) and [docs](https://docs.axolotl.ai/docs/sequence_parallelism.html) to learn how to scale your context length when fine-tuning.
- 2025/06: Magistral with mistral-common tokenizer support has been added to Axolotl. See [docs](https://docs.axolotl.ai/docs/models/magistral.html) to start training your own Magistral models with Axolotl!
- 2025/04: Llama 4 support has been added in Axolotl. See [docs](https://docs.axolotl.ai/docs/models/llama-4.html) to start training your own Llama 4 models with Axolotl's linearized version!
+- 2025/06: Magistral with mistral-common tokenizer support has been added to Axolotl. See [examples](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/magistral) to start training your own Magistral models with Axolotl!
+- 2025/04: Llama 4 support has been added in Axolotl. See [examples](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/llama-4) to start training your own Llama 4 models with Axolotl's linearized version!
 - 2025/03: (Beta) Fine-tuning Multimodal models is now supported in Axolotl. Check out the [docs](https://docs.axolotl.ai/docs/multimodal.html) to fine-tune your own!
 - 2025/02: Axolotl has added LoRA optimizations to reduce memory usage and improve training speed for LoRA and QLoRA in single GPU and multi-GPU training (DDP and DeepSpeed). Jump into the [docs](https://docs.axolotl.ai/docs/lora_optims.html) to give it a try.
 - 2025/02: Axolotl has added GRPO support. Dive into our [blog](https://huggingface.co/blog/axolotl-ai-co/training-llms-w-interpreter-feedback-wasm) and [GRPO example](https://github.com/axolotl-ai-cloud/grpo_code) and have some fun!
@@ -69,15 +65,9 @@ Features:
 - **Flexible Dataset Handling**: Load from local, HuggingFace, and cloud (S3, Azure, GCP, OCI) datasets.
 - **Cloud Ready**: We ship [Docker images](https://hub.docker.com/u/axolotlai) and also [PyPI packages](https://pypi.org/project/axolotl/) for use on cloud platforms and local hardware.

-
-
 ## 🚀 Quick Start - LLM Fine-tuning in Minutes

-**Requirements**:
-
- NVIDIA GPU (Ampere or newer for `bf16` and Flash Attention) or AMD GPU
- Python 3.11
- PyTorch ≥2.8.0
+**Requirements**: NVIDIA GPU (Ampere+) or AMD GPU, Python 3.11+

 ### Google Colab

@@ -85,15 +75,35 @@ Features:

 ### Installation

-#### Using pip
+#### Project setup (uv add)

 ```bash
-pip3 install -U packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation axolotl[flash-attn,deepspeed]
+# Install uv
+curl -LsSf https://astral.sh/uv/install.sh | sh
+
+# Initialize or enter your project
+uv init my-project && cd my-project
+uv add axolotl
+uv pip install flash-attn --no-build-isolation
+source .venv/bin/activate

 # Download example axolotl configs, deepspeed configs
 axolotl fetch examples
-axolotl fetch deepspeed_configs  # OPTIONAL
+axolotl fetch deepspeed_configs  # optional
+```
+
+#### Quick try (uv pip)
+
+```bash
+# Install uv if needed
+curl -LsSf https://astral.sh/uv/install.sh | sh
+
+uv pip install axolotl
+uv pip install flash-attn --no-build-isolation
+
+# Download example axolotl configs, deepspeed configs
+axolotl fetch examples
+axolotl fetch deepspeed_configs  # optional
 ```

 #### Using Docker
@@ -158,13 +168,6 @@ That's it! Check out our [Getting Started Guide](https://docs.axolotl.ai/docs/ge

 Contributions are welcome! Please see our [Contributing Guide](https://github.com/axolotl-ai-cloud/axolotl/blob/main/.github/CONTRIBUTING.md) for details.

-## 📈 Telemetry
-
-Axolotl has opt-out telemetry that helps us understand how the project is being used
-and prioritize improvements. We collect basic system information, model types, and
-error rates—never personal data or file paths. Telemetry is enabled by default. To
-disable it, set AXOLOTL_DO_NOT_TRACK=1. For more details, see our [telemetry documentation](https://docs.axolotl.ai/docs/telemetry.html).
-
 ## ❤️ Sponsors

 Interested in sponsoring? Contact us at [wing@axolotl.ai](mailto:wing@axolotl.ai)
--- a/1
+++ b/1
@@ -1 +0,0 @@
-0.15.0.dev0
--- a/_quarto.yml
+++ b/_quarto.yml
@@ -1,8 +1,6 @@
 project:
  type: website
-  pre-render:
-   - docs/scripts/generate_config_docs.py
-   - docs/scripts/generate_examples_docs.py
+  pre-render: docs/scripts/generate_config_docs.py

 quartodoc:
  dir: docs/api
@@ -242,48 +240,7 @@ website:
            - docs/getting-started.qmd
            - docs/installation.qmd
            - docs/inference.qmd
-            - section: "Model Guides"
-              contents:
-                - docs/models/kimi-linear.qmd
-                - docs/models/plano.qmd
-                - docs/models/mimo.qmd
-                - docs/models/internvl3_5.qmd
-                - docs/models/olmo3.qmd
-                - docs/models/trinity.qmd
-                - docs/models/arcee.qmd
-                - section: "Ministral3"
-                  contents:
-                    - docs/models/ministral3.qmd
-                    - docs/models/ministral3/think.qmd
-                    - docs/models/ministral3/vision.qmd
-                - section: "Magistral"
-                  contents:
-                    - docs/models/magistral.qmd
-                    - docs/models/magistral/think.qmd
-                    - docs/models/magistral/vision.qmd
-                - docs/models/ministral.qmd
-                - docs/models/mistral-small.qmd
-                - docs/models/voxtral.qmd
-                - docs/models/devstral.qmd
-                - docs/models/mistral.qmd
-                - docs/models/llama-4.qmd
-                - docs/models/llama-2.qmd
-                - docs/models/qwen3-next.qmd
-                - docs/models/qwen3.qmd
-                - docs/models/gemma3n.qmd
-                - docs/models/apertus.qmd
-                - docs/models/gpt-oss.qmd
-                - docs/models/seed-oss.qmd
-                - docs/models/phi.qmd
-                - docs/models/smolvlm2.qmd
-                - docs/models/granite4.qmd
-                - docs/models/LiquidAI.qmd
-                - docs/models/hunyuan.qmd
-                - docs/models/jamba.qmd
-                - docs/models/orpheus.qmd
-
            - docs/cli.qmd
-            - docs/telemetry.qmd
            - docs/config-reference.qmd
            - text: "API Reference"
              href: docs/api
@@ -320,7 +277,6 @@ website:
            - docs/multipack.qmd
            - docs/mixed_precision.qmd
            - docs/optimizers.qmd
-            - docs/attention.qmd

        - section: "Advanced Features"
          contents:
--- a/cicd/Dockerfile-uv.jinja
+++ b/cicd/Dockerfile-uv.jinja
@@ -1,53 +0,0 @@
-FROM axolotlai/axolotl-base-uv:{{ BASE_TAG }}
-
-ENV TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
-ENV AXOLOTL_EXTRAS="{{ AXOLOTL_EXTRAS }}"
-ENV AXOLOTL_ARGS="{{ AXOLOTL_ARGS }}"
-ENV CUDA="{{ CUDA }}"
-ENV PYTORCH_VERSION="{{ PYTORCH_VERSION }}"
-ENV GITHUB_REF="{{ GITHUB_REF }}"
-ENV GITHUB_SHA="{{ GITHUB_SHA }}"
-ENV NIGHTLY_BUILD="{{ NIGHTLY_BUILD }}"
-ENV HF_HOME="{{ HF_HOME }}"
-
-RUN apt-get update && \
-    apt-get install -y --allow-change-held-packages vim curl nano libnccl2 libnccl-dev ibverbs-providers ibverbs-utils infiniband-diags librdmacm-dev librdmacm1 rdmacm-utils slurm-wlm
-
-WORKDIR /workspace
-
-RUN git clone --depth=1 https://github.com/axolotl-ai-cloud/axolotl.git
-
-WORKDIR /workspace/axolotl
-
-RUN git fetch origin +$GITHUB_REF && \
-    git checkout FETCH_HEAD
-
-# If AXOLOTL_EXTRAS is set, append it in brackets
-RUN if [ "$NIGHTLY_BUILD" = "true" ] ; then \
-        sed -i 's#^transformers.*#transformers @ git+https://github.com/huggingface/transformers.git@main#' requirements.txt; \
-        sed -i 's#^peft.*#peft @ git+https://github.com/huggingface/peft.git@main#' requirements.txt; \
-        sed -i 's#^accelerate.*#accelerate @ git+https://github.com/huggingface/accelerate.git@main#' requirements.txt; \
-        sed -i 's#^trl.*#trl @ git+https://github.com/huggingface/trl.git@main#' requirements.txt; \
-        sed -i 's#^datasets.*#datasets @ git+https://github.com/huggingface/datasets.git@main#' requirements.txt; \
-    fi
-
-RUN uv pip install packaging==26.0 setuptools==75.8.0
-RUN uv pip install torchvision
-RUN if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
-        uv pip install --no-build-isolation -e .[deepspeed,flash-attn,ring-flash-attn,optimizers,ray,$AXOLOTL_EXTRAS] $AXOLOTL_ARGS; \
-    else \
-        uv pip install --no-build-isolation -e .[deepspeed,flash-attn,ring-flash-attn,optimizers,ray] $AXOLOTL_ARGS; \
-    fi
-
-RUN python scripts/unsloth_install.py --uv | sh
-RUN python scripts/cutcrossentropy_install.py --uv | sh
-
-# So we can test the Docker image
-RUN uv pip install -r requirements-dev.txt -r requirements-tests.txt
-
-# fix so that git fetch/pull from remote works
-RUN git config remote.origin.fetch "+refs/heads/*:refs/remotes/origin/*" && \
-    git config --get remote.origin.fetch
-
-# helper for huggingface-login cli
-RUN git config --global credential.helper store
--- a/cicd/Dockerfile.jinja
+++ b/cicd/Dockerfile.jinja
@@ -1,6 +1,10 @@
-FROM axolotlai/axolotl-base:{{ BASE_TAG }}
+FROM axolotlai/axolotl-base-uv:{{ BASE_TAG }}

-ENV TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
+SHELL ["/bin/bash", "-euxo", "pipefail", "-c"]
+
+ARG VENV_PYTHON="/workspace/axolotl-venv/bin/python"
+
+ENV TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
 ENV AXOLOTL_EXTRAS="{{ AXOLOTL_EXTRAS }}"
 ENV AXOLOTL_ARGS="{{ AXOLOTL_ARGS }}"
 ENV CUDA="{{ CUDA }}"
@@ -9,7 +13,7 @@ ENV GITHUB_REF="{{ GITHUB_REF }}"
 ENV GITHUB_SHA="{{ GITHUB_SHA }}"
 ENV NIGHTLY_BUILD="{{ NIGHTLY_BUILD }}"
 ENV HF_HOME="{{ HF_HOME }}"
-ENV AXOLOTL_DATASET_NUM_PROC="8"
+ENV VENV_PYTHON=$VENV_PYTHON

 RUN apt-get update && \
    apt-get install -y --allow-change-held-packages vim curl nano libnccl2 libnccl-dev ibverbs-providers ibverbs-utils infiniband-diags librdmacm-dev librdmacm1 rdmacm-utils slurm-wlm
@@ -25,25 +29,27 @@ RUN git fetch origin +$GITHUB_REF && \

 # If AXOLOTL_EXTRAS is set, append it in brackets
 RUN if [ "$NIGHTLY_BUILD" = "true" ] ; then \
-        sed -i 's#^transformers.*#transformers @ git+https://github.com/huggingface/transformers.git@main#' requirements.txt; \
-        sed -i 's#^peft.*#peft @ git+https://github.com/huggingface/peft.git@main#' requirements.txt; \
-        sed -i 's#^accelerate.*#accelerate @ git+https://github.com/huggingface/accelerate.git@main#' requirements.txt; \
-        sed -i 's#^trl.*#trl @ git+https://github.com/huggingface/trl.git@main#' requirements.txt; \
-        sed -i 's#^datasets.*#datasets @ git+https://github.com/huggingface/datasets.git@main#' requirements.txt; \
+        sed -i 's#"transformers[^"]*"#"transformers @ git+https://github.com/huggingface/transformers.git@main"#' pyproject.toml; \
+        sed -i 's#"peft[^"]*"#"peft @ git+https://github.com/huggingface/peft.git@main"#' pyproject.toml; \
+        sed -i 's#"accelerate[^"]*"#"accelerate @ git+https://github.com/huggingface/accelerate.git@main"#' pyproject.toml; \
+        sed -i 's#"trl[^"]*"#"trl @ git+https://github.com/huggingface/trl.git@main"#' pyproject.toml; \
+        sed -i 's#"datasets[^"]*"#"datasets @ git+https://github.com/huggingface/datasets.git@main"#' pyproject.toml; \
    fi

-RUN pip install packaging==26.0 setuptools==75.8.0 psutil
+RUN uv pip install --python "$VENV_PYTHON" packaging==23.2 setuptools==75.8.0 pip
 RUN if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
-        pip install --no-build-isolation -e .[deepspeed,flash-attn,ring-flash-attn,optimizers,ray,$AXOLOTL_EXTRAS] $AXOLOTL_ARGS; \
+        uv pip install --python "$VENV_PYTHON" --no-build-isolation -e .[ring-flash-attn,optimizers,ray,${AXOLOTL_EXTRAS}] $AXOLOTL_ARGS; \
    else \
-        pip install --no-build-isolation -e .[deepspeed,flash-attn,ring-flash-attn,optimizers,ray] $AXOLOTL_ARGS; \
+        uv pip install --python "$VENV_PYTHON" --no-build-isolation -e .[ring-flash-attn,optimizers,ray] $AXOLOTL_ARGS; \
    fi

-RUN python scripts/unsloth_install.py | sh
-RUN python scripts/cutcrossentropy_install.py | sh
+RUN uv pip install --python "$VENV_PYTHON" --no-build-isolation flash-attn $AXOLOTL_ARGS
+
+RUN "$VENV_PYTHON" scripts/unsloth_install.py | sh
+RUN "$VENV_PYTHON" scripts/cutcrossentropy_install.py | sh

 # So we can test the Docker image
-RUN pip install -r requirements-dev.txt -r requirements-tests.txt
+RUN uv pip install --python "$VENV_PYTHON" -e ".[dev]"

 # fix so that git fetch/pull from remote works
 RUN git config remote.origin.fetch "+refs/heads/*:refs/remotes/origin/*" && \
--- a/cicd/cicd.sh
+++ b/cicd/cicd.sh
@@ -4,7 +4,7 @@ set -e
 python -c "import torch; assert '$PYTORCH_VERSION' in torch.__version__"

 # Run unit tests with initial coverage report
-pytest -v --durations=10 -n8 \
+uv run pytest -v --durations=10 -n8 \
  --ignore=tests/e2e/ \
  --ignore=tests/patched/ \
  --ignore=tests/cli \
@@ -12,36 +12,36 @@ pytest -v --durations=10 -n8 \
  --cov=axolotl

 # Run lora kernels tests with coverage append
-pytest -v --durations=10 \
+uv run pytest -v --durations=10 \
  /workspace/axolotl/tests/e2e/patched/lora_kernels \
  --cov=axolotl \
  --cov-append

 # Run patched tests excluding lora kernels with coverage append
-pytest --full-trace -vvv --durations=10 \
+uv run pytest --full-trace -vvv --durations=10 \
  --ignore=tests/e2e/patched/lora_kernels \
  /workspace/axolotl/tests/e2e/patched \
  --cov=axolotl \
  --cov-append

 # Run solo tests with coverage append
-pytest -v --durations=10 -n1 \
+uv run pytest -v --durations=10 -n1 \
  /workspace/axolotl/tests/e2e/solo/ \
  --cov=axolotl \
  --cov-append

 # Run integration tests with coverage append
-pytest -v --durations=10 \
+uv run pytest -v --durations=10 \
  /workspace/axolotl/tests/e2e/integrations/ \
  --cov=axolotl \
  --cov-append

-pytest -v --durations=10 /workspace/axolotl/tests/cli \
+uv run pytest -v --durations=10 /workspace/axolotl/tests/cli \
  --cov=axolotl \
  --cov-append

 # Run remaining e2e tests with coverage append and final report
-pytest -v --durations=10 \
+uv run pytest -v --durations=10 \
  --ignore=tests/e2e/solo/ \
  --ignore=tests/e2e/patched/ \
  --ignore=tests/e2e/multigpu/ \
@@ -52,4 +52,4 @@ pytest -v --durations=10 \
  --cov-append \
  --cov-report=xml:e2e-coverage.xml

-codecov upload-process -t $CODECOV_TOKEN -f e2e-coverage.xml -F e2e,pytorch-${PYTORCH_VERSION} || true
+uv run codecov upload-process -t $CODECOV_TOKEN -f e2e-coverage.xml -F e2e,pytorch-${PYTORCH_VERSION} || true
--- a/cicd/multigpu.py
+++ b/cicd/multigpu.py
@@ -17,22 +17,18 @@ template_loader = jinja2.FileSystemLoader(searchpath=cicd_path)
 template_env = jinja2.Environment(
    loader=template_loader, autoescape=select_autoescape()
 )
-dockerfile = os.environ.get("E2E_DOCKERFILE", "Dockerfile.jinja")
-df_template = template_env.get_template(dockerfile)
+df_template = template_env.get_template("Dockerfile.jinja")

 df_args = {
    "AXOLOTL_EXTRAS": os.environ.get("AXOLOTL_EXTRAS", ""),
    "AXOLOTL_ARGS": os.environ.get("AXOLOTL_ARGS", ""),
    "PYTORCH_VERSION": os.environ.get("PYTORCH_VERSION", "2.6.0"),
-    "BASE_TAG": os.environ.get("BASE_TAG", "main-base-py3.11-cu126-2.6.0"),
+    "BASE_TAG": os.environ.get("BASE_TAG", "main-base-uv-py3.11-cu126-2.6.0"),
    "CUDA": os.environ.get("CUDA", "126"),
    "GITHUB_REF": os.environ.get("GITHUB_REF", "refs/heads/main"),
    "GITHUB_SHA": os.environ.get("GITHUB_SHA", ""),
-    "NIGHTLY_BUILD": os.environ.get("NIGHTLY_BUILD", ""),
    "CODECOV_TOKEN": os.environ.get("CODECOV_TOKEN", ""),
    "HF_HOME": "/workspace/data/huggingface-cache/hub",
-    "PYTHONUNBUFFERED": os.environ.get("PYTHONUNBUFFERED", "1"),
-    "DEEPSPEED_LOG_LEVEL": os.environ.get("DEEPSPEED_LOG_LEVEL", "WARNING"),
 }

 dockerfile_contents = df_template.render(**df_args)
--- a/cicd/multigpu.sh
+++ b/cicd/multigpu.sh
@@ -2,7 +2,7 @@
 set -e

 # Only run two tests at a time to avoid OOM on GPU (with coverage collection)
-pytest -v --durations=10 -n2 --maxfail=3 \
+pytest -v --durations=10 -n2 \
  --ignore=/workspace/axolotl/tests/e2e/multigpu/solo/ \
  --ignore=/workspace/axolotl/tests/e2e/multigpu/patched/ \
  /workspace/axolotl/tests/e2e/multigpu/ \
--- a/cicd/single_gpu.py
+++ b/cicd/single_gpu.py
@@ -23,7 +23,7 @@ df_args = {
    "AXOLOTL_EXTRAS": os.environ.get("AXOLOTL_EXTRAS", ""),
    "AXOLOTL_ARGS": os.environ.get("AXOLOTL_ARGS", ""),
    "PYTORCH_VERSION": os.environ.get("PYTORCH_VERSION", "2.6.0"),
-    "BASE_TAG": os.environ.get("BASE_TAG", "main-base-py3.11-cu126-2.6.0"),
+    "BASE_TAG": os.environ.get("BASE_TAG", "main-base-uv-py3.11-cu126-2.6.0"),
    "CUDA": os.environ.get("CUDA", "126"),
    "GITHUB_REF": os.environ.get("GITHUB_REF", "refs/heads/main"),
    "GITHUB_SHA": os.environ.get("GITHUB_SHA", ""),
@@ -65,13 +65,8 @@ def run_cmd(cmd: str, run_folder: str):
    import subprocess  # nosec

    sp_env = os.environ.copy()
-    sp_env["AXOLOTL_DATASET_NUM_PROC"] = "8"
+    sp_env["AXOLOTL_DATASET_PROCESSES"] = "8"

    # Propagate errors from subprocess.
-    try:
-        exit_code = subprocess.call(cmd.split(), cwd=run_folder, env=sp_env)  # nosec
-        if exit_code:
-            print(f"Command '{cmd}' failed with exit code {exit_code}")
-            return exit_code
-    except Exception as e:  # pylint: disable=broad-except
-        print(f"Command '{cmd}' failed with exception {e}")
+    if exit_code := subprocess.call(cmd.split(), cwd=run_folder, env=sp_env):  # nosec
+        exit(exit_code)
--- a/devtools/dev_chat_template.yml
+++ b/devtools/dev_chat_template.yml
@@ -13,7 +13,7 @@ datasets:
 val_set_size: 0
 output_dir: temp_debug/axolotl_outputs/model
 dataset_prepared_path: temp_debug/axolotl_outputs/data
-dataset_num_proc: 1
+dataset_processes: 1

 sequence_len: 4096
 sample_packing: false
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -1,14 +1,19 @@
-ARG BASE_TAG=main-base
-FROM axolotlai/axolotl-base:$BASE_TAG
+ARG BASE_TAG=main-base-uv
+FROM axolotlai/axolotl-base-uv:$BASE_TAG

 ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6+PTX"
 ARG AXOLOTL_EXTRAS=""
 ARG AXOLOTL_ARGS=""
 ARG CUDA="118"
 ARG PYTORCH_VERSION="2.1.2"
-ARG TARGETARCH
+ARG GIT_REF="refs/heads/main"
+ARG GIT_SHA="HEAD"
+ARG VENV_PYTHON="/workspace/axolotl-venv/bin/python"

 ENV PYTORCH_VERSION=$PYTORCH_VERSION
+ENV GIT_REF=$GIT_REF
+ENV GIT_SHA=$GIT_SHA
+ENV VENV_PYTHON=$VENV_PYTHON

 RUN apt-get update && \
    apt-get install -y --allow-change-held-packages vim curl nano libnccl2 libnccl-dev rsync s3fs && \
@@ -21,20 +26,19 @@ RUN git clone --depth=1 https://github.com/axolotl-ai-cloud/axolotl.git

 WORKDIR /workspace/axolotl

-# If AXOLOTL_EXTRAS is set, append it in brackets; don't install deepspeed with arm64
-RUN if [ "$TARGETARCH" = "arm64" ]; then \
-        BASE_EXTRAS="flash-attn,ring-flash-attn,optimizers,ray"; \
+# Ensure we are on the expected commit and break Docker cache between revisions
+RUN git fetch origin "$GIT_REF" && git checkout "$GIT_SHA"
+
+# If AXOLOTL_EXTRAS is set, append it in brackets
+RUN if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
+        uv pip install --python "$VENV_PYTHON" --no-build-isolation -e .[ring-flash-attn,optimizers,ray,$AXOLOTL_EXTRAS] $AXOLOTL_ARGS; \
    else \
-        BASE_EXTRAS="deepspeed,flash-attn,ring-flash-attn,optimizers,ray"; \
+        uv pip install --python "$VENV_PYTHON" --no-build-isolation -e .[ring-flash-attn,optimizers,ray] $AXOLOTL_ARGS; \
    fi && \
-    if [ "$AXOLOTL_EXTRAS" != "" ]; then \
-        pip install --no-build-isolation -e .[$BASE_EXTRAS,$AXOLOTL_EXTRAS] $AXOLOTL_ARGS; \
-    else \
-        pip install --no-build-isolation -e .[$BASE_EXTRAS] $AXOLOTL_ARGS; \
-    fi && \    python scripts/unsloth_install.py | sh && \
-    python scripts/cutcrossentropy_install.py | sh && \
-    pip install pytest && \
-    pip cache purge
+    uv pip install --python "$VENV_PYTHON" --no-build-isolation flash-attn $AXOLOTL_ARGS && \
+    "$VENV_PYTHON" scripts/unsloth_install.py | sh && \
+    "$VENV_PYTHON" scripts/cutcrossentropy_install.py | sh && \
+    uv pip install --python "$VENV_PYTHON" pytest

 # fix so that git fetch/pull from remote works with shallow clone
 RUN git config remote.origin.fetch "+refs/heads/*:refs/remotes/origin/*" && \
--- a/docker/Dockerfile-base
+++ b/docker/Dockerfile-base
@@ -2,16 +2,14 @@ ARG CUDA_VERSION="11.8.0"
 ARG CUDNN_VERSION="8"
 ARG UBUNTU_VERSION="22.04"
 ARG MAX_JOBS=4
-ARG TARGETARCH

 FROM nvidia/cuda:$CUDA_VERSION-cudnn$CUDNN_VERSION-devel-ubuntu$UBUNTU_VERSION AS base-builder

 ENV PATH="/root/miniconda3/bin:${PATH}"

-ARG TARGETARCH
-ARG PYTHON_VERSION="3.11"
+ARG PYTHON_VERSION="3.10"
 ARG PYTORCH_VERSION="2.1.2"
-ARG CUDA="128"
+ARG CUDA="118"
 ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"

 ENV PYTHON_VERSION=$PYTHON_VERSION
@@ -24,17 +22,11 @@ RUN apt-get update \
        librdmacm-dev librdmacm1 rdmacm-utils slurm-wlm \
    && rm -rf /var/cache/apt/archives \
    && rm -rf /var/lib/apt/lists/* \
-    && if [ "$TARGETARCH" = "amd64" ]; then \
-        MINICONDA_ARCH="x86_64"; \
-    elif [ "$TARGETARCH" = "arm64" ]; then \
-        MINICONDA_ARCH="aarch64"; \
-    else \
-        echo "Unsupported architecture: $TARGETARCH"; exit 1; \
-    fi \
-    && wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-${MINICONDA_ARCH}.sh \
+    && wget \
+    https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh \
    && mkdir /root/.conda \
-    && bash Miniconda3-latest-Linux-${MINICONDA_ARCH}.sh -b \
-    && rm -f Miniconda3-latest-Linux-${MINICONDA_ARCH}.sh \
+    && bash Miniconda3-latest-Linux-x86_64.sh -b \
+    && rm -f Miniconda3-latest-Linux-x86_64.sh \
    && conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/main \
    && conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/r \
    && conda create -n "py${PYTHON_VERSION}" python="${PYTHON_VERSION}"
@@ -43,50 +35,18 @@ ENV PATH="/root/miniconda3/envs/py${PYTHON_VERSION}/bin:${PATH}"

 WORKDIR /workspace

-RUN python3 -m pip install --upgrade pip && pip3 install -U packaging==26.0 setuptools==75.8.0 wheel psutil && \
+RUN python3 -m pip install --upgrade pip && pip3 install -U packaging==23.2 setuptools==75.8.0 wheel && \
    python3 -m pip install --no-cache-dir -U torch==${PYTORCH_VERSION}+cu${CUDA} torchvision --extra-index-url https://download.pytorch.org/whl/cu$CUDA && \
+    CAUSAL_CONV1D_FORCE_CXX11_ABI=TRUE CAUSAL_CONV1D_FORCE_BUILD=TRUE python3 -m pip install --no-cache-dir causal_conv1d==1.5.2 && \
+    python3 -m pip install --no-cache-dir "mamba_ssm @ git+https://github.com/state-spaces/mamba.git@main" && \
    python3 -m pip cache purge

-RUN if [ "$CUDA" != "130" ] ; then \
-        CAUSAL_CONV1D_FORCE_CXX11_ABI=TRUE CAUSAL_CONV1D_FORCE_BUILD=TRUE python3 -m pip install --no-cache-dir "causal_conv1d @ git+https://github.com/Dao-AILab/causal-conv1d.git@v1.5.4"; \
-        python3 -m pip install --no-cache-dir "mamba_ssm @ git+https://github.com/state-spaces/mamba.git@main"; \
-        python3 -m pip cache purge; \
-    fi
-
 RUN git lfs install --skip-repo && \
    pip3 install awscli && \
    # The base image ships with `pydantic==1.8.2` which is not working
    pip3 install -U --no-cache-dir pydantic==1.10.10 && \
    pip3 cache purge

-RUN case "$PYTORCH_VERSION" in \
-        2.9.[0-9]*) \
-            if [ "$CUDA" = "128" ]; then \
-                if [ "$TARGETARCH" = "amd64" ]; then \
-                    WHL_FILE="flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl"; \
-                    WHL_VERSION="v0.5.4"; \
-                elif [ "$TARGETARCH" = "arm64" ]; then \
-                    WHL_FILE="flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_aarch64.whl"; \
-                    WHL_VERSION="v0.6.4"; \
-                else \
-                    echo "Unsupported architecture: $TARGETARCH"; exit 1; \
-                fi; \
-                wget -nv https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/${WHL_VERSION}/${WHL_FILE}; \
-                pip3 install --no-cache-dir ${WHL_FILE}; \
-                rm ${WHL_FILE}; \
-            elif [ "$CUDA" = "130" ]; then \
-                if [ "$TARGETARCH" = "amd64" ]; then \
-                    WHL_FILE="flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_x86_64.whl"; \
-                    WHL_VERSION="v0.5.4"; \
-                elif [ "$TARGETARCH" = "arm64" ]; then \
-                    WHL_FILE="flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_aarch64.whl"; \
-                    WHL_VERSION="v0.6.4"; \
-                else \
-                    echo "Unsupported architecture: $TARGETARCH"; exit 1; \
-                fi; \
-                wget -nv https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/${WHL_VERSION}/${WHL_FILE}; \
-                pip3 install --no-cache-dir ${WHL_FILE}; \
-                rm ${WHL_FILE}; \
-            fi \
-            ;; \
-    esac
+RUN if [ "$PYTORCH_VERSION" = "2.6.0" ] && [ "$CUDA" = "124" ] ; then \
+        FLASH_ATTENTION_FORCE_BUILD="TRUE" uv pip install --no-build-isolation flash-attn==2.8.0.post2; \
+    fi
--- a/docker/Dockerfile-base-nightly
+++ b/docker/Dockerfile-base-nightly
@@ -30,7 +30,7 @@ ENV PATH="/root/miniconda3/envs/py${PYTHON_VERSION}/bin:${PATH}"

 WORKDIR /workspace

-RUN python3 -m pip install --upgrade pip && pip3 install -U packaging==26.0 setuptools==75.8.0 wheel && \
+RUN python3 -m pip install --upgrade pip && pip3 install -U packaging==23.2 setuptools==75.8.0 wheel && \
    python3 -m pip install --no-cache-dir -U torch --extra-index-url https://download.pytorch.org/whl/nightly/cu$CUDA && \
    python3 -m pip install --no-cache-dir "causal_conv1d @ git+https://github.com/Dao-AILab/causal-conv1d.git@main" && \
    python3 -m pip install --no-cache-dir "mamba_ssm @ git+https://github.com/state-spaces/mamba.git@main" && \
--- a/docker/Dockerfile-cloud
+++ b/docker/Dockerfile-cloud
@@ -12,8 +12,8 @@ EXPOSE 22
 COPY scripts/cloud-entrypoint.sh /root/cloud-entrypoint.sh
 COPY scripts/motd /etc/motd

-RUN pip install jupyterlab notebook ipywidgets && \
-    jupyter lab clean
+RUN uv pip install --python "$VENV_PYTHON" jupyterlab notebook ipywidgets && \
+    "$VENV_PYTHON" -m jupyter lab clean
 RUN apt update && \
    apt install --yes --no-install-recommends openssh-server tmux iproute2 nvtop && \
    rm -rf /var/cache/apt/archives && \
--- a/docker/Dockerfile-cloud-no-tmux
+++ b/docker/Dockerfile-cloud-no-tmux
@@ -12,8 +12,8 @@ EXPOSE 22
 COPY scripts/cloud-entrypoint.sh /root/cloud-entrypoint.sh
 COPY scripts/motd /etc/motd

-RUN pip install jupyterlab notebook ipywidgets && \
-    jupyter lab clean
+RUN uv pip install --python "$VENV_PYTHON" jupyterlab notebook ipywidgets && \
+    "$VENV_PYTHON" -m jupyter lab clean
 RUN apt update && \
    apt install --yes --no-install-recommends openssh-server tmux iproute2 nvtop ibverbs-providers ibverbs-utils infiniband-diags librdmacm-dev librdmacm1 rdmacm-utils slurm-wlm && \
    rm -rf /var/cache/apt/archives && \
--- a/docker/Dockerfile-tests
+++ b/docker/Dockerfile-tests
@@ -24,13 +24,14 @@ RUN git fetch origin +$GITHUB_REF && \

 # If AXOLOTL_EXTRAS is set, append it in brackets
 RUN if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
-        pip install --no-build-isolation -e .[deepspeed,flash-attn,mamba-ssm,$AXOLOTL_EXTRAS] $AXOLOTL_ARGS; \
+        uv pip install --no-build-isolation -e .[deepspeed,mamba-ssm,$AXOLOTL_EXTRAS] $AXOLOTL_ARGS; \
    else \
-        pip install --no-build-isolation -e .[deepspeed,flash-attn,mamba-ssm] $AXOLOTL_ARGS; \
-    fi
+        uv pip install --no-build-isolation -e .[deepspeed,mamba-ssm] $AXOLOTL_ARGS; \
+    fi && \
+    uv pip install --no-build-isolation flash-attn $AXOLOTL_ARGS

 # So we can test the Docker image
-RUN pip install pytest
+RUN uv pip install pytest

 # fix so that git fetch/pull from remote works
 RUN git config remote.origin.fetch "+refs/heads/*:refs/remotes/origin/*" && \
--- a/docker/Dockerfile-uv-base
+++ b/docker/Dockerfile-uv-base
@@ -2,7 +2,6 @@ ARG CUDA_VERSION="12.6.3"
 ARG CUDNN_VERSION=""
 ARG UBUNTU_VERSION="22.04"
 ARG MAX_JOBS=4
-ARG TARGETARCH

 FROM nvidia/cuda:$CUDA_VERSION-cudnn$CUDNN_VERSION-devel-ubuntu$UBUNTU_VERSION AS base-builder

@@ -14,6 +13,7 @@ ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
 ENV PYTHON_VERSION=$PYTHON_VERSION
 ENV TORCH_CUDA_ARCH_LIST=$TORCH_CUDA_ARCH_LIST
 ENV UV_TORCH_BACKEND="cu${CUDA}"
+ENV VENV_PYTHON=/workspace/axolotl-venv/bin/python

 RUN apt-get update \
    && apt-get install -y wget git build-essential ninja-build git-lfs libaio-dev pkg-config curl && rm -rf /var/lib/apt/lists/* \
@@ -30,37 +30,8 @@ RUN uv venv --no-project --relocatable axolotl-venv

 ENV PATH="/workspace/axolotl-venv/bin:${PATH}"

-RUN uv pip install packaging setuptools wheel psutil \
-    && uv pip install torch==${PYTORCH_VERSION} torchvision \
-    && uv pip install awscli pydantic
-
-RUN if [ "$TARGETARCH" = "amd64" ]; then \
-        uv pip install --no-build-isolation "causal_conv1d @ git+https://github.com/Dao-AILab/causal-conv1d.git@main"; \
-        uv pip install "mamba_ssm @ git+https://github.com/state-spaces/mamba.git@main"; \
-    fi
-
-RUN case "$PYTORCH_VERSION" in \
-        2.9.[0-9]*) \
-            if [ "$TARGETARCH" = "amd64" ]; then \
-                if [ "$CUDA" = "128" ]; then \
-                    wget -nv https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.5.4/flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl; \
-                    uv pip install --no-cache-dir flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl; \
-                    rm flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl; \
-                elif [ "$CUDA" = "130" ]; then \
-                    wget -nv https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.5.4/flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_x86_64.whl; \
-                    uv pip install --no-cache-dir flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_x86_64.whl; \
-                    rm flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_x86_64.whl; \
-                fi \
-            elif [ "$TARGETARCH" = "arm64" ]; then \
-                if [ "$CUDA" = "128" ]; then \
-                    wget -nv https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.6.4/flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_aarch64.whl; \
-                    uv pip install --no-cache-dir flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_aarch64.whl; \
-                    rm flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_aarch64.whl; \
-                elif [ "$CUDA" = "130" ]; then \
-                    wget -nv https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.6.4/flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_aarch64.whl; \
-                    uv pip install --no-cache-dir flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_aarch64.whl; \
-                    rm flash_attn-2.8.3+cu130torch2.9-cp311-cp311-linux_aarch64.whl; \
-                fi \
-            fi \
-            ;; \
-    esac
+RUN uv pip install --python "$VENV_PYTHON" packaging setuptools wheel psutil protobuf grpclib \
+    && uv pip install --python "$VENV_PYTHON" torch==${PYTORCH_VERSION} \
+    && uv pip install --python "$VENV_PYTHON" --no-build-isolation "causal_conv1d @ git+https://github.com/Dao-AILab/causal-conv1d.git@main" \
+    && uv pip install --python "$VENV_PYTHON" "mamba_ssm @ git+https://github.com/state-spaces/mamba.git@main" \
+    && uv pip install --python "$VENV_PYTHON" awscli pydantic
--- a/docs/.gitignore
+++ b/docs/.gitignore
@@ -3,5 +3,3 @@ _site/
 /api/*.qmd
 /api/*.html
 config-reference.qmd
-models/**/*.qmd
-models/**/*.html
--- a/docs/amd_hpc.qmd
+++ b/docs/amd_hpc.qmd
@@ -86,7 +86,7 @@ export HF_DATASETS_OFFLINE=1
 Download a base model using the Hugging Face CLI:

 ```bash
-hf download meta-llama/Meta-Llama-3.1-8B --local-dir ~/hfdata/llama3.1-8B
+huggingface-cli download meta-llama/Meta-Llama-3.1-8B --local-dir ~/hfdata/llama3.1-8B
 ```

 ### 10. Create Axolotl Configuration
--- a/docs/attention.qmd
+++ b/docs/attention.qmd
@@ -1,140 +0,0 @@
---
-title: Attention
-description: Supported attention modules in Axolotl
---
-
-## SDP Attention
-
-This is the default built-in attention in PyTorch.
-
-```yaml
-sdp_attention: true
-```
-
-For more details: [PyTorch docs](https://docs.pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html)
-
-## Flash Attention 2
-
-Uses efficient kernels to compute attention.
-
-```yaml
-flash_attention: true
-```
-
-For more details: [Flash Attention](https://github.com/Dao-AILab/flash-attention/)
-
-### Nvidia
-
-Requirements: Ampere, Ada, or Hopper GPUs
-
-Note: For Turing GPUs or lower, please use other attention methods.
-
-```bash
-pip install flash-attn --no-build-isolation
-```
-
-::: {.callout-tip}
-
-If you get `undefined symbol` while training, ensure you installed PyTorch prior to Axolotl. Alternatively, try reinstall or downgrade a version.
-
-:::
-
-#### Flash Attention 3
-
-Requirements: Hopper only and CUDA 12.8 (recommended)
-
-```bash
-git clone https://github.com/Dao-AILab/flash-attention.git
-cd flash-attention/hopper
-
-python setup.py install
-```
-
-### AMD
-
-Requirements: ROCm 6.0 and above.
-
-See [Flash Attention AMD docs](https://github.com/Dao-AILab/flash-attention/tree/main?tab=readme-ov-file#amd-rocm-support).
-
-## Flex Attention
-
-A flexible PyTorch API for attention used in combination with `torch.compile`.
-
-```yaml
-flex_attention: true
-
-# recommended
-torch_compile: true
-```
-
-::: {.callout-note}
-
-We recommend using latest stable version of PyTorch for best performance.
-
-:::
-
-For more details: [PyTorch docs](https://pytorch.org/blog/flexattention/)
-
-## SageAttention
-
-Attention kernels with QK Int8 and PV FP16 accumulator.
-
-```yaml
-sage_attention: true
-```
-
-Requirements: Ampere, Ada, or Hopper GPUs
-
-```bash
-pip install sageattention==2.2.0 --no-build-isolation
-```
-
-::: {.callout-warning}
-
-Only LoRA/QLoRA recommended at the moment. We found loss drop to 0 for full finetuning. See [GitHub Issue](https://github.com/thu-ml/SageAttention/issues/198).
-
-:::
-
-For more details: [Sage Attention](https://github.com/thu-ml/SageAttention)
-
-::: {.callout-note}
-
-We do not support SageAttention 3 at the moment. If you are interested on adding this or improving SageAttention implementation, please make an Issue.
-
-:::
-
-
-## xFormers
-
-```yaml
-xformers_attention: true
-```
-
-::: {.callout-tip}
-
-We recommend using with Turing GPUs or below (such as on Colab).
-
-:::
-
-For more details: [xFormers](https://github.com/facebookresearch/xformers)
-
-## Shifted Sparse Attention
-
-::: {.callout-warning}
-
-We plan to deprecate this! If you use this feature, we recommend switching to methods above.
-
-:::
-
-Requirements: LLaMA model architecture
-
-```yaml
-flash_attention: true
-s2_attention: true
-```
-
-::: {.callout-tip}
-
-No sample packing support!
-
-:::
--- a/docs/checkpoint_saving.qmd
+++ b/docs/checkpoint_saving.qmd
@@ -1,86 +0,0 @@
---
-title: "Checkpoint Saving"
-format:
-  html:
-    toc: true
-    toc-depth: 2
-    number-sections: true
-execute:
-  enabled: false
---
-
-## Overview
-
-Axolotl supports on-demand checkpoint saving during training. You can trigger checkpoints via file-based triggers (for programmatic control) or Control+C (for interactive use).
-
-## File-Based Checkpoint Trigger
-
-### Configuration
-
-Enable in your config:
-
-```yaml
-dynamic_checkpoint:
-  enabled: true
-  check_interval: 100  # Optional: check every N steps (default: 100)
-  trigger_file_path: "axolotl_checkpoint.save"  # Optional: custom filename
-```
-
-**Options:**
- `enabled`: `true` to enable (required)
- `check_interval`: Steps between file checks. Default: 100. Lower = faster response, higher I/O overhead.
- `trigger_file_path`: Custom trigger filename. Default: `axolotl_checkpoint.save`
-
-### How It Works
-
-1. Rank 0 checks for trigger file every `check_interval` steps in `output_dir`
-2. When detected, file is deleted and checkpoint is saved
-3. In distributed training, rank 0 broadcasts to synchronize all ranks
-
-### Usage
-
-**Command line:**
-```bash
-touch /path/to/output_dir/axolotl_checkpoint.save
-```
-
-**Programmatic:**
-```python
-from pathlib import Path
-Path("/path/to/output_dir/axolotl_checkpoint.save").touch()
-```
-
-Checkpoint saves within the next `check_interval` steps. The trigger file is auto-deleted after detection, so you can create it multiple times.
-
-**Custom filename:**
-```yaml
-dynamic_checkpoint:
-  enabled: true
-  trigger_file_path: "my_trigger.save"
-```
-```bash
-touch /path/to/output_dir/my_trigger.save
-```
-
-## Control+C (SIGINT) Checkpoint
-
-Pressing `Ctrl+C` during training saves the model state and exits gracefully. **Note:** This saves only the model weights, not optimizer state. For resumable checkpoints, use the file-based trigger.
-
-## Best Practices
-
- **Check interval**: Lower values (10-50) for fast training, default 100 for slower training
- **Distributed training**: Create trigger file once; rank 0 handles synchronization
- **Resume**: Dynamic checkpoints can be resumed like regular checkpoints via `resume_from_checkpoint`
-
-## Example
-
-```yaml
-output_dir: ./outputs/lora-out
-save_steps: 500  # Scheduled checkpoints
-
-dynamic_checkpoint:
-  enabled: true
-  check_interval: 50
-```
-
-This enables scheduled checkpoints every 500 steps plus on-demand saves via file trigger (checked every 50 steps).
--- a/docs/dataset-formats/conversation.qmd
+++ b/docs/dataset-formats/conversation.qmd
@@ -218,13 +218,6 @@ If you have tool arguments with same name but different dtypes (like `"time": st
 ```
 "arguments": "{\"...\": \"...\"}"
 ```
-
-The same is applicable for tool parameters.
-
-```
-"parameters": "{\"...\": \"...\"}"
-```
-
 :::

 Example config for Llama4:
--- a/docs/debugging.qmd
+++ b/docs/debugging.qmd
@@ -29,7 +29,7 @@ While debugging it's helpful to simplify your test scenario as much as possible.
 1. **Make sure you are using the latest version of axolotl**:  This project changes often and bugs get fixed fast.  Check your git branch and make sure you have pulled the latest changes from `main`.
 1. **Eliminate concurrency**: Restrict the number of processes to 1 for both training and data preprocessing:
    - Set `CUDA_VISIBLE_DEVICES` to a single GPU, ex: `export CUDA_VISIBLE_DEVICES=0`.
-    - Set `dataset_num_proc: 1` in your axolotl config or run the training command with `--dataset_num_proc=1`.
+    - Set `dataset_processes: 1` in your axolotl config or run the training command with `--dataset_processes=1`.
 2. **Use a small dataset**: Construct or use a small dataset from HF Hub. When using a small dataset, you will often have to make sure `sample_packing: False` and `eval_sample_packing: False` to avoid errors.  If you are in a pinch and don't have time to construct a small dataset but want to use from the HF Hub, you can shard the data (this will still tokenize the entire dataset, but will only use a fraction of the data for training.  For example, to shard the dataset into 20 pieces, add the following to your axolotl config):

    ```yaml
@@ -72,8 +72,8 @@ datasets:
 Make sure you have an [editable install](https://setuptools.pypa.io/en/latest/userguide/development_mode.html) of Axolotl, which ensures that changes you make to the code are reflected at runtime.  Run the following commands from the root of this project:

 ```bash
-pip3 install packaging
-pip3 install --no-build-isolation -e '.[flash-attn,deepspeed]'
+uv sync --extra deepspeed
+uv pip install flash-attn --no-build-isolation
 ```

 #### Remote Hosts
@@ -101,7 +101,7 @@ For example, to mimic the command `cd devtools && CUDA_VISIBLE_DEVICES=0 acceler
                "-m", "axolotl.cli.train", "dev_chat_template.yml",
                // The flags below simplify debugging by overriding the axolotl config
                // with the debugging tips above.  Modify as needed.
-                "--dataset_num_proc=1",      // limits data preprocessing to one process
+                "--dataset_processes=1",      // limits data preprocessing to one process
                "--max_steps=1",              // limits training to just one step
                "--batch_size=1",             // minimizes batch size
                "--micro_batch_size=1",       // minimizes batch size
@@ -213,8 +213,8 @@ docker run --privileged --gpus '"all"' --shm-size 10g --rm -it --name axolotl --
 You will now be in the container.  Next, perform an editable install of Axolotl:

 ```bash
-pip3 install packaging
-pip3 install --no-build-isolation -e '.[flash-attn,deepspeed]'
+uv sync --extra deepspeed
+uv pip install flash-attn --no-build-isolation
 ```

 ### Attach To Container
--- a/docs/docker.qmd
+++ b/docs/docker.qmd
@@ -32,8 +32,11 @@ main-base-py{python_version}-cu{cuda_version}-{pytorch_version}

 Tags examples:

- `main-base-py3.11-cu128-2.8.0`
- `main-base-py3.11-cu128-2.9.1`
+- `main-base-py3.11-cu128-2.7.1`
+- `main-base-py3.11-cu126-2.7.1`
+- `main-base-py3.11-cu126-2.7.0`
+- `main-base-py3.11-cu126-2.6.0`
+- `main-base-py3.11-cu124-2.6.0`

 ## Main

@@ -71,12 +74,15 @@ There may be some extra tags appended to the image, like `-vllm` which installs

 Tags examples:

- `main-py3.11-cu128-2.8.0`
- `main-py3.11-cu128-2.9.1`
+- `main-py3.11-cu128-2.7.1`
+- `main-py3.11-cu126-2.7.1`
+- `main-py3.11-cu126-2.7.0`
+- `main-py3.11-cu126-2.6.0`
+- `main-py3.11-cu124-2.6.0`
 - `main-latest`
 - `main-20250303-py3.11-cu124-2.6.0`
 - `main-20250303-py3.11-cu126-2.6.0`
- `0.12.0`
+- `0.10.1`

 ## Cloud

--- a/docs/faq.qmd
+++ b/docs/faq.qmd
@@ -63,14 +63,6 @@ description: Frequently asked questions

 > A: There seems to be a wheel issue with FA2 2.8.0 on CUDA 12.4. Try CUDA 12.6 instead or downgrade to FA2 2.7.4. Please refer to the upstream issue: https://github.com/Dao-AILab/flash-attention/issues/1717.

-**Q: Can we mix text and text+image datasets for VLM training?**
-
-> A: Yes, you can for newer VLM arch. The ones that would not work are LLaVA / Pixtral arch. If you notice one not working, please let us know!
-
-**Q: Why is `memory/max_*` different from `nvidia-smi`?**
-
-> A: We use `torch` APIs to retrieve this information. You can see https://docs.pytorch.org/docs/stable/notes/cuda.html#cuda-memory-management for more information.
-
 ### Chat templates

 **Q: `jinja2.exceptions.UndefinedError: 'dict object' has no attribute 'content' / 'role' / ____`**
--- a/docs/installation.qmd
+++ b/docs/installation.qmd
@@ -26,22 +26,43 @@ Follow the instructions at: [https://pytorch.org/get-started/locally/](https://p
 :::

 ::: {.callout-important}
-For Blackwell GPUs, please use Pytorch 2.9.1 and CUDA 12.8.
+For Blackwell GPUs, please use Pytorch 2.7.0 and CUDA 12.8.
 :::

-### PyPI Installation (Recommended) {#sec-pypi}
+### uv Installation (Recommended) {#sec-uv-quick}

 ```{.bash}
-pip3 install -U packaging setuptools wheel ninja
-pip3 install --no-build-isolation axolotl[flash-attn,deepspeed]
+# Install uv if not already installed
+curl -LsSf https://astral.sh/uv/install.sh | sh
+
+# Add Axolotl to a project (recommended)
+uv init my-project && cd my-project
+uv add axolotl
+uv pip install flash-attn --no-build-isolation
+source .venv/bin/activate
+```
+
+For a quick one-off install without creating a project:
+
+```{.bash}
+uv pip install axolotl
+uv pip install flash-attn --no-build-isolation
+```
+
+### pip Installation {#sec-pypi}
+
+```{.bash}
+pip install --no-build-isolation axolotl[deepspeed]
+pip install --no-build-isolation flash-attn
 ```

 We use `--no-build-isolation` in order to detect the installed PyTorch version (if
 installed) in order not to clobber it, and so that we set the correct version of
 dependencies that are specific to the PyTorch version or other installed
-co-dependencies.
+co-dependencies. Flash Attention is resolved separately so it can be built against
+the environment configured by the previous step.

-### uv Installation {#sec-uv}
+### Advanced uv Installation {#sec-uv}

 uv is a fast, reliable Python package installer and resolver built in Rust. It offers significant performance improvements over pip and provides better dependency resolution, making it an excellent choice for complex environments.

@@ -62,28 +83,38 @@ source .venv/bin/activate
 Install PyTorch
 - PyTorch 2.6.0 recommended
 ```{.bash}
-uv pip install packaging setuptools wheel
 uv pip install torch==2.6.0
 uv pip install awscli pydantic
 ```

 Install axolotl from PyPi
 ```{.bash}
-uv pip install --no-build-isolation axolotl[deepspeed,flash-attn]
-
+uv pip install --no-build-isolation axolotl[deepspeed]
 # optionally install with vLLM if you're using torch==2.6.0 and want to train w/ GRPO
-uv pip install --no-build-isolation axolotl[deepspeed,flash-attn,vllm]
+# uv pip install --no-build-isolation axolotl[deepspeed,vllm]
+
+uv pip install flash-attn --no-build-isolation
 ```

 ### Edge/Development Build {#sec-edge-build}

 For the latest features between releases:

+#### Using uv (recommended)
 ```{.bash}
 git clone https://github.com/axolotl-ai-cloud/axolotl.git
 cd axolotl
-pip3 install -U packaging setuptools wheel ninja
-pip3 install --no-build-isolation -e '.[flash-attn,deepspeed]'
+curl -LsSf https://astral.sh/uv/install.sh | sh  # If not already installed
+uv sync
+uv pip install flash-attn --no-build-isolation
+```
+
+#### Using pip
+```{.bash}
+git clone https://github.com/axolotl-ai-cloud/axolotl.git
+cd axolotl
+pip install --no-build-isolation -e '.[deepspeed]'
+pip install --no-build-isolation flash-attn
 ```

 ### Docker {#sec-docker}
@@ -111,7 +142,7 @@ docker run --privileged --gpus '"all"' --shm-size 10g --rm -it \
 :::

 ::: {.callout-important}
-For Blackwell GPUs, please use `axolotlai/axolotl:main-py3.11-cu128-2.9.1` or the cloud variant `axolotlai/axolotl-cloud:main-py3.11-cu128-2.9.1`.
+For Blackwell GPUs, please use `axolotlai/axolotl:main-py3.11-cu128-2.7.0` or the cloud variant `axolotlai/axolotl-cloud:main-py3.11-cu128-2.7.0`.
 :::

 Please refer to the [Docker documentation](docker.qmd) for more information on the different Docker images that are available.
@@ -141,7 +172,7 @@ For providers supporting Docker:
 ### macOS {#sec-macos}

 ```{.bash}
-pip3 install --no-build-isolation -e '.'
+uv pip install --no-build-isolation -e '.'
 ```

 See @sec-troubleshooting for Mac-specific issues.
@@ -159,13 +190,18 @@ We recommend using WSL2 (Windows Subsystem for Linux) or Docker.
 1. Install Python ≥3.11
 2. Install PyTorch: https://pytorch.org/get-started/locally/
 3. Install Axolotl:
-   ```{.bash}
-   pip3 install -U packaging setuptools wheel ninja
-   pip3 install --no-build-isolation -e '.[flash-attn,deepspeed]'
-   ```
+```{.bash}
+# Option A: add Axolotl to the environment
+uv add axolotl
+uv pip install flash-attn --no-build-isolation
+
+# Option B: quick install
+uv pip install axolotl
+uv pip install flash-attn --no-build-isolation
+```
 4. (Optional) Login to Hugging Face:
   ```{.bash}
-   hf auth login
+   huggingface-cli login
   ```

 ## Troubleshooting {#sec-troubleshooting}
--- a/docs/lora_optims.qmd
+++ b/docs/lora_optims.qmd
@@ -89,10 +89,6 @@ lora_o_kernel: true
 Currently, LoRA kernels are not supported for RLHF training, only SFT.
 :::

-::: {.callout-warning}
-LoRA kernels do not support remote modeling code.
-:::
-
 ## Requirements

 - One or more NVIDIA or AMD GPUs (in order to use the Triton kernels)
--- a/docs/lr_groups.qmd
+++ b/docs/lr_groups.qmd
@@ -27,9 +27,3 @@ learning_rate: 2e-5
 In this example, we have a default learning rate of 2e-5 across the entire model, but we have a separate learning rate
 of 1e-6 for all the self attention `o_proj` modules across all layers, and a learning are of 1e-5 to the 3rd layer's
 self attention `q_proj` module.
-
-::: {.callout-note}
-
-We currently only support varying `lr` for now. If you're interested in adding support for others (`weight_decay`), we welcome PRs. See https://github.com/axolotl-ai-cloud/axolotl/blob/613bcf90e58f3ab81d3827e7fc572319908db9fb/src/axolotl/core/trainers/mixins/optimizer.py#L17
-
-:::
--- a/docs/multi-gpu.qmd
+++ b/docs/multi-gpu.qmd
@@ -4,7 +4,7 @@ format:
  html:
    toc: true
    toc-depth: 3
-    # number-sections: true
+    number-sections: true
    code-tools: true
 execute:
  enabled: false
@@ -14,18 +14,12 @@ This guide covers advanced training configurations for multi-GPU setups using Ax

 ## Overview {#sec-overview}

-When training on multiple GPUs, Axolotl supports 3 sharding/parallelism strategies. Additionally, you can layer specific optimization features on top of that strategy.
+Axolotl supports several methods for multi-GPU training:

-You generally cannot combine these strategies; they are mutually exclusive.
-
-1.  **DeepSpeed**: Powerful optimization library, supports ZeRO stages 1-3.
-2.  **FSDP (Fully Sharded Data Parallel)**: PyTorch's native sharding implementation (Recommended).
-3.  **DDP (Distributed Data Parallel)**: PyTorch's native parallelism implementation (Default if neither of the above are selected).
-
-These features can often be combined with the strategies above:
-
-*   **Sequence Parallelism**: Splits long sequences across GPUs (Compatible with DDP, DeepSpeed, and FSDP).
-*   **FSDP + QLoRA**: Combines 4-bit quantization with FSDP (Specific to FSDP).
+- DeepSpeed (recommended)
+- FSDP (Fully Sharded Data Parallel)
+- Sequence parallelism
+- FSDP + QLoRA

 ## DeepSpeed {#sec-deepspeed}

@@ -71,18 +65,12 @@ Start from Stage 1 -> Stage 2 -> Stage 3.

 ## Fully Sharded Data Parallel (FSDP) {#sec-fsdp}

-FSDP allows you to shard model parameters, gradients, and optimizer states across data parallel workers.
-
 ::: {.callout-note}

 FSDP2 is recommended for new users. FSDP1 is deprecated and will be removed in an upcoming release of Axolotl.

 :::

-### FSDP + QLoRA {#sec-fsdp-qlora}
-
-For combining FSDP with QLoRA, see our [dedicated guide](fsdp_qlora.qmd).
-
 ### Migrating from FSDP1 to FSDP2 {#sec-migrate-fsdp1-fsdp2}

 To migrate your config from FSDP1 to FSDP2, you must use the `fsdp_version` top-level config field to specify the FSDP version, and
@@ -100,7 +88,6 @@ fsdp_sync_module_states | **REMOVED**
 fsdp_cpu_ram_efficient_loading | cpu_ram_efficient_loading
 fsdp_state_dict_type | state_dict_type
 fsdp_use_orig_params | **REMOVED**
-fsdp_activation_checkpointing | activation_checkpointing

 For more details, please see the migration guide in the [torchtitan repo](https://github.com/pytorch/torchtitan/blob/main/docs/fsdp.md). In Axolotl,
 if you were using the following FSDP1 config:
@@ -157,6 +144,10 @@ single sequence causes OOM errors during model training.

 See our [dedicated guide](sequence_parallelism.qmd) for more information.

+### FSDP + QLoRA {#sec-fsdp-qlora}
+
+For combining FSDP with QLoRA, see our [dedicated guide](fsdp_qlora.qmd).
+
 ## Performance Optimization {#sec-performance}

 ### Liger Kernel Integration {#sec-liger}
--- a/docs/multimodal.qmd
+++ b/docs/multimodal.qmd
@@ -19,10 +19,8 @@ format:
 - [Gemma-3n](#sec-gemma-3n)
 - [Qwen2-VL](#sec-qwen2-vl)
 - [Qwen2.5-VL](#sec-qwen25-vl)
- [GLM-4.6V](#sec-glm-4-6v)
 - [SmolVLM2](#sec-smolvlm2)
 - [LFM2-VL](#sec-lfm2-vl)
- [Intern-VL](#sec-intern-vl)

 ## Usage

@@ -58,14 +56,10 @@ image_resize_algorithm: bilinear

 Please see [examples](https://github.com/axolotl-ai/axolotl/tree/main/examples) folder for full configs.

-::: {.callout-tip}
+::: {.callout-warning}
 Some of our chat_templates have been extended to support broader dataset types. This should not break any existing configs.
 :::

-::: {.callout-note}
-As of now, we do not truncate nor drop samples based on `sequence_len` as each arch has different ways to process non-text tokens. We are looking for help on this.
-:::
-
 ### Mllama {#sec-mllama}

 ```yaml
@@ -101,7 +95,7 @@ chat_template: llava
 ### Mistral-Small-3.1 {#sec-mistral-small-31}

 ::: {.callout-tip}
-Please make sure to install vision lib via `pip install 'mistral-common[opencv]==1.8.5'`
+Please make sure to install vision lib via `uv pip install 'mistral-common[opencv]==1.8.5'`
 :::

 ```yaml
@@ -111,7 +105,7 @@ base_model: mistralai/Mistral-Small-3.1-24B-Instruct-2503
 ### Magistral-Small-2509 {#sec-magistral-small-2509}

 ::: {.callout-tip}
-Please make sure to install vision lib via `pip install 'mistral-common[opencv]==1.8.5'`
+Please make sure to install vision lib via `uv pip install 'mistral-common[opencv]==1.8.5'`
 :::

 ```yaml
@@ -121,13 +115,11 @@ base_model: mistralai/Magistral-Small-2509
 ### Voxtral {#sec-voxtral}

 ::: {.callout-tip}
-Please make sure to install audio lib via `pip3 install librosa==0.11.0 'mistral_common[audio]==1.8.3'`
+Please make sure to install audio lib via `uv pip install librosa==0.11.0 'mistral_common[audio]==1.8.3'`
 :::

 ```yaml
 base_model: mistralai/Voxtral-Mini-3B-2507
-
-processor_type: VoxtralProcessor
 ```

 ### Gemma-3 {#sec-gemma-3}
@@ -151,7 +143,7 @@ The model's initial loss and grad norm will be very high. We suspect this to be
 :::

 ::: {.callout-tip}
-Please make sure to install `timm` via `pip3 install timm==1.0.17`
+Please make sure to install `timm` via `uv pip install timm==1.0.17`
 :::

 ```yaml
@@ -176,30 +168,10 @@ base_model: Qwen/Qwen2.5-VL-7B-Instruct
 chat_template: qwen2_vl  # same as qwen2-vl
 ```

-### Qwen3-VL {#sec-qwen3-vl}
-
-```yaml
-base_model: Qwen/Qwen3-VL-4B-Instruct
-
-chat_template: qwen2_vl  # same as qwen2-vl
-```
-
-### GLM-4.6V {#sec-glm-4-6v}
-
-Both GLM-4.6V (106B MoE) and GLM-4.6V-Flash (9B) are supported.
-
-```yaml
-# GLM-4.6V (106B MoE version)
-base_model: zai-org/GLM-4.6V
-
-# OR GLM-4.6V-Flash (9B version)
-base_model: zai-org/GLM-4.6V-Flash
-```
-
 ### SmolVLM2 {#sec-smolvlm2}

 ::: {.callout-tip}
-Please make sure to install `num2words` via `pip3 install num2words==0.5.14`
+Please make sure to install `num2words` via `uv pip install num2words==0.5.14`
 :::

 ```yaml
@@ -209,23 +181,13 @@ base_model: HuggingFaceTB/SmolVLM2-500M-Video-Instruct
 ### LFM2-VL {#sec-lfm2-vl}

 ::: {.callout-warning}
-Please uninstall `causal-conv1d` via `pip3 uninstall -y causal-conv1d`
+Please uninstall `causal-conv1d` via `uv pip uninstall -y causal-conv1d`
 :::

 ```yaml
 base_model: LiquidAI/LFM2-VL-450M
 ```

-### Intern-VL {#sec-intern-vl}
-
-::: {.callout-tip}
-Please make sure to install `timm` via `pip3 install timm==1.0.19`
-:::
-
-```yaml
-base_model: OpenGVLab/InternVL3_5-8B
-```
-
 ## Dataset Format

 For multi-modal datasets, we adopt an extended `chat_template` format similar to OpenAI's Message format.
@@ -260,7 +222,7 @@ For audio loading, you can use the following keys within `content` alongside `"t

 ::: {.callout-tip}

-You may need to install `librosa` via `pip3 install librosa==0.11.0`.
+You may need to install `librosa` via `uv pip install librosa==0.11.0`.

 :::

--- a/docs/rlhf.qmd
+++ b/docs/rlhf.qmd
@@ -17,7 +17,6 @@ feedback. Various methods include, but not limited to:
 - [Kahneman-Tversky Optimization (KTO)](#kto)
 - [Odds Ratio Preference Optimization (ORPO)](#orpo)
 - [Group Relative Policy Optimization (GRPO)](#grpo)
- [Group Reward-Decoupled Policy Optimization (GDPO)](#gdpo)


 ## RLHF using Axolotl
@@ -220,21 +219,6 @@ DPO supports the following types with the following dataset format:
 }
 ```

-#### chat_template.argilla_chat
-
-```json
-{
-    "chosen": [
-        {"role": "user", "content": "..."},
-        {"role": "assistant", "content": "..."}
-    ],
-    "rejected": [
-        {"role": "user", "content": "..."},
-        {"role": "assistant", "content": "..."}
-    ]
-}
-```
-
 #### chat_template.default

 ```yaml
@@ -598,116 +582,6 @@ To see other examples of custom reward functions, please see [TRL GRPO Docs](htt

 To see all configs, please see [TRLConfig](https://github.com/axolotl-ai-cloud/axolotl/blob/v0.9.2/src/axolotl/utils/schemas/trl.py).

-#### OpenEnv Rollout Functions
-
-GRPO supports custom rollout functions for OpenEnv-style environments, enabling interactive tasks like web browsing, code execution, or tool use. This allows you to implement custom generation logic that interacts with external environments.
-
-For example, to implement a simple math-solving environment with step-by-step verification:
-
-```python
-# math_env.py
-import re
-
-def math_solver_rollout(model, processing_class, prompts, generation_config=None):
-    """
-    Custom rollout function that generates step-by-step math solutions.
-
-    Args:
-        model: The language model
-        processing_class: The tokenizer/processing_class
-        prompts: List of prompt dicts (with 'messages' key for chat format)
-        generation_config: Optional generation configuration
-
-    Returns:
-        List of completion strings
-    """
-    completions = []
-
-    for prompt in prompts:
-        # Apply chat template to prompt
-        messages = prompt.get("messages", [])
-        formatted_prompt = processing_class.apply_chat_template(
-            messages, processing_class=False, add_generation_prompt=True
-        )
-
-        # Generate step-by-step solution
-        full_response = ""
-        for step in range(5):  # Max 5 reasoning steps
-            current_input = formatted_prompt + full_response + "\nNext step:"
-            inputs = processing_class(current_input, return_tensors="pt").to(model.device)
-
-            outputs = model.generate(
-                **inputs,
-                max_new_tokens=100,
-                generation_config=generation_config,
-            )
-            step_text = processing_class.decode(
-                outputs[0][inputs.input_ids.shape[1]:],
-                skip_special_tokens=True
-            )
-
-            # Check if solution is complete
-            if "FINAL ANSWER:" in step_text:
-                full_response += step_text
-                break
-            full_response += step_text + "\n"
-
-        completions.append(full_response)
-
-    return completions
-
-def math_reward(prompts, completions, answers, **kwargs):
-    """Reward function that checks mathematical correctness"""
-    rewards = []
-    for completion, correct_answer in zip(completions, answers):
-        # Extract predicted answer
-        match = re.search(r"FINAL ANSWER:\s*(.+)", completion)
-        predicted = match.group(1).strip() if match else ""
-
-        # Compare with correct answer
-        reward = 1.0 if predicted == str(correct_answer) else 0.0
-        rewards.append(reward)
-
-    return rewards
-
-def math_transform(cfg, *args, **kwargs):
-    """Transform dataset to GRPO format with answer field"""
-    def transform_fn(example, processing_class=None):
-        return {
-            "prompt": [{"role": "user", "content": example["question"]}],
-            "answer": str(example["answer"]),
-        }
-    return transform_fn, {"remove_columns": ["question"]}
-```
-
-```yaml
-rl: grpo
-
-trl:
-  beta: 0.001
-  max_completion_length: 512
-  num_generations: 4
-  rollout_func: "math_env.math_solver_rollout"  # Custom rollout function
-  reward_funcs: ["math_env.math_reward"]
-  reward_weights: [1.0]
-
-datasets:
-  - path: openai/gsm8k
-    name: main
-    type: math_env.math_transform
-```
-
-The `rollout_func` parameter accepts a fully qualified name (e.g., `module_name.function_name`) that points to a callable function in your local directory. The function receives:
-
- `model`: The language model
- `processing_class`: The tokenizer/processing class
- `prompts`: List of prompt dictionaries
- `generation_config` (optional): Generation configuration
-
-And should return a list of completion strings.
-
-For more OpenEnv examples, see [TRL OpenEnv Documentation](https://huggingface.co/docs/trl/main/en/openenv).
-
 #### GRPO with DAPO/Dr. GRPO loss

 The DAPO paper and subsequently Dr. GRPO paper proposed an alternative loss function for GRPO to remediate the penalty in longer responses.
@@ -721,102 +595,6 @@ trl:

 For more information, see [GRPO docs](https://huggingface.co/docs/trl/v0.17.0/en/grpo_trainer#loss-types).

-### GDPO
-
-GDPO (Group Reward-Decoupled Policy Optimization) extends GRPO for multi-reward training. It addresses the **reward advantage collapse** problem by normalizing each reward function independently before combining them.
-
-::: {.callout-tip}
-Use GDPO when training with multiple reward functions. For single reward, GRPO and GDPO produce equivalent results.
-:::
-
-Paper: [https://arxiv.org/pdf/2501.05242](https://arxiv.org/pdf/2501.05242)
-
-GDPO uses TRL's native `multi_objective_aggregation` parameter under the hood. When you set `rl: gdpo`, axolotl automatically configures TRL to use `normalize_then_sum` aggregation.
-
-```yaml
-base_model: Qwen/Qwen2.5-1.5B-Instruct
-
-vllm:
-    host: 0.0.0.0
-    port: 8000
-    tensor_parallel_size: 2
-    gpu_memory_utilization: 0.85
-
-rl: gdpo
-
-trl:
-    beta: 0.001
-    max_completion_length: 256
-    use_vllm: true
-    num_generations: 4
-    reward_funcs:
-        - rewards.format_reward
-        - rewards.correctness_reward
-    reward_weights: [1.0, 2.0]
-
-datasets:
-    - path: openai/gsm8k
-      name: main
-      type: rewards.oai_gsm8k_transform
-```
-
-You can also use GRPO with explicit aggregation control:
-
-```yaml
-rl: grpo
-trl:
-    multi_objective_aggregation: normalize_then_sum  # GDPO behavior
-    # or: sum_then_normalize  # Default GRPO behavior
-```
-
-#### GDPO vs GRPO
-
-| Aspect | GRPO | GDPO |
-|--------|------|------|
-| **Aggregation** | `sum_then_normalize` | `normalize_then_sum` |
-| **Multi-reward** | May collapse advantages | Preserves reward signals |
-| **Single reward** | Standard behavior | Equivalent to GRPO |
-
-#### Why GDPO?
-
-When using multiple rewards with GRPO, different reward combinations can produce identical advantages:
-
-```
-# Example: format + correctness rewards
-[format=0, correct=3] → sum=3
-[format=1, correct=2] → sum=3  ← GRPO sees these as equal!
-[format=2, correct=1] → sum=3
-[format=3, correct=0] → sum=3
-```
-
-GDPO normalizes each reward independently, preserving their relative differences.
-
-#### Reward Functions
-
-GDPO uses the same reward function format as GRPO:
-
-```python
-# rewards.py
-def format_reward(completions, **kwargs) -> list[float]:
-    return [1.0 if len(c) > 10 else 0.0 for c in completions]
-
-def correctness_reward(completions, answers, **kwargs) -> list[float]:
-    rewards = []
-    for completion, answer in zip(completions, answers):
-        # Your scoring logic here
-        rewards.append(score)
-    return rewards
-```
-
-#### Sequence Parallelism
-
-GDPO supports sequence parallelism for long-context training:
-
-```yaml
-rl: gdpo
-context_parallel_size: 2
-```
-
 ### SimPO

 SimPO uses [CPOTrainer](https://huggingface.co/docs/trl/main/en/cpo_trainer) but with alternative loss function.
--- a/docs/scripts/examples-allowlist.yml
+++ b/docs/scripts/examples-allowlist.yml
@@ -1,90 +0,0 @@
-examples:
-  # December 2025
-  - name: kimi-linear
-    title: Kimi Linear
-  - name: plano
-    title: Plano Orchestrator
-  - name: mimo
-    title: MiMo
-  - name: internvl3_5
-    title: InternVL 3.5
-
-  # AllenAI
-  - name: olmo3
-    title: OLMo 3
-
-  # ArceeAI
-  - name: trinity
-    title: Trinity
-  - name: arcee
-    title: Arcee AFM
-
-  # MistralAI
-  - name: ministral3/think
-    title: Ministral 3 Thinking
-  - name: ministral3/vision
-    title: Ministral 3 Vision
-  - name: magistral/think
-    title: Magistral Thinking
-  - name: magistral/vision
-    title: Magistral Vision
-  - name: ministral
-    title: Ministral
-  - name: mistral-small
-    title: Mistral Small 3.1/3.2
-  - name: voxtral
-    title: Voxtral
-  - name: devstral
-    title: Devstral
-  - name: mistral
-    title: Mistral 7B
-
-  # Meta
-  - name: llama-4
-    title: Llama 4
-  - name: llama-2
-    title: Llama 2
-
-  # Alibaba
-  - name: qwen3-next
-    title: Qwen 3 Next
-  - name: qwen3
-    title: Qwen 3
-
-  # Google
-  - name: gemma3n
-    title: Gemma 3n
-
-  # Swiss AI
-  - name: apertus
-    title: Apertus
-
-  # GPT-OSS
-  - name: gpt-oss
-    title: GPT-OSS
-  - name: seed-oss
-    title: Seed-OSS
-
-  # Microsoft
-  - name: phi
-    title: Phi
-
-  # SmolVLM
-  - name: smolvlm2
-    title: SmolVLM 2
-
-  # IBM
-  - name: granite4
-    title: Granite 4
-
-  # LiquidAI
-  - name: LiquidAI
-    title: Liquid Foundation Models 2
-
-  # Other
-  - name: hunyuan
-    title: Hunyuan
-  - name: jamba
-    title: Jamba
-  - name: orpheus
-    title: Orpheus
--- a/docs/scripts/generate_examples_docs.py
+++ b/docs/scripts/generate_examples_docs.py
@@ -1,424 +0,0 @@
-"""
-auto generate example docs from allowlist
-"""
-
-import re
-import shutil
-import sys
-from pathlib import Path
-
-import yaml
-
-# Paths
-THIS = Path(__file__).resolve()
-ROOT = THIS.parents[2]  # repo root (docs/scripts -> docs -> ROOT)
-EXAMPLES_DIR = ROOT / "examples"
-OUTPUT_DIR = ROOT / "docs" / "models"
-ALLOWLIST_YML = THIS.parent / "examples-allowlist.yml"
-
-
-def slugify(name: str) -> str:
-    """Convert a name to a slug (lowercase, hyphens for spaces)."""
-    s = re.sub(r"[^a-zA-Z0-9\s\-]+", "", name.strip())
-    s = re.sub(r"\s+", "-", s).strip("-").lower()
-    return s or "example"
-
-
-def read_allowlist():
-    with open(ALLOWLIST_YML, "r", encoding="utf-8") as f:
-        data = yaml.safe_load(f) or {}
-    items = data.get("examples", [])
-    if not isinstance(items, list):
-        raise ValueError("`examples` must be a list in examples-allowlist.yml")
-    return items
-
-
-def find_readme(folder: Path) -> Path | None:
-    for name in ("README.md", "Readme.md", "readme.md"):
-        p = folder / name
-        if p.exists():
-            return p
-    return None
-
-
-def remove_first_h1(md: str) -> tuple[str, str | None]:
-    """
-    Remove the first H1 from markdown and return (modified_md, h1_title).
-    The H1 is removed since we use the frontmatter title instead.
-    """
-    lines = md.splitlines()
-    result = []
-    h1_title = None
-    skipped_first = False
-
-    for line in lines:
-        if not skipped_first and line.startswith("# "):
-            h1_title = line[2:].strip()
-            skipped_first = True
-            continue
-        result.append(line)
-
-    return "\n".join(result), h1_title
-
-
-IMG_RE = re.compile(r"!\[[^\]]*\]\(([^)]+)\)")
-LINK_RE = re.compile(r"\[([^\]]+)\]\(([^)]+)\)")
-
-
-def rewrite_and_copy_assets(md: str, src_dir: Path, dest_assets_root: Path) -> str:
-    """
-    Copy local image assets referenced in markdown to
-    docs/examples/assets/... and rewrite the links.
-    """
-    dest_assets = dest_assets_root / "assets"
-
-    def repl(m):
-        url = m.group(1).strip()
-        if re.match(r"^(https?:)?//", url):
-            return m.group(0)  # leave remote URLs
-        src_path = (src_dir / url).resolve()
-        if not src_path.exists():
-            return m.group(0)  # leave as-is if not found
-        rel = src_path.relative_to(src_dir)
-        # Create a unique asset path based on source directory name
-        asset_name = src_dir.name.replace("/", "-")
-        dest_path = dest_assets / asset_name / rel
-        dest_path.parent.mkdir(parents=True, exist_ok=True)
-        shutil.copy2(src_path, dest_path)
-        new_rel = f"assets/{asset_name}/{rel.as_posix()}"
-        return m.group(0).replace(url, new_rel)
-
-    return IMG_RE.sub(repl, md)
-
-
-def rewrite_readme_links(
-    md: str,
-    src_dir: Path,
-    examples_dir: Path,
-    parent_index_only: set,
-    current_src_path: str,
-    allowlist_entries: set,
-    current_output_path: str,
-) -> str:
-    """
-    Rewrite links between README.md files to point to the correct .qmd files.
-    """
-
-    def repl(m):
-        text = m.group(1)
-        url = m.group(2).strip()
-
-        # Skip remote URLs and anchor links
-        if re.match(r"^(https?:)?//", url) or url.startswith("#"):
-            return m.group(0)
-
-        # Skip non-markdown files
-        if not url.lower().endswith(".md"):
-            return m.group(0)
-
-        # Resolve the target path
-        try:
-            target_path = (src_dir / url).resolve()
-
-            # Check if target is outside examples_dir
-            try:
-                rel_path = target_path.relative_to(examples_dir)
-            except ValueError:
-                # Target is outside examples_dir, leave as-is
-                return m.group(0)
-
-            parts = list(rel_path.parts)
-
-            # Determine the output path for the target
-            if len(parts) > 0 and parts[-1].lower() in ("readme.md", "readme"):
-                # This is a README link
-                if len(parts) == 1:
-                    # Link to root README -> index.qmd
-                    target_output = "index.qmd"
-                elif len(parts) == 2:
-                    if parts[0] == ".":
-                        # Current directory README
-                        target_output = "index.qmd"
-                    else:
-                        # subdir/README.md
-                        parent_dir = parts[0]
-                        if parent_dir in parent_index_only:
-                            target_output = f"{parent_dir}/index.qmd"
-                        else:
-                            target_output = f"{parent_dir}.qmd"
-                else:
-                    # Deeper nesting: parent/subdir/README.md
-                    # Build the full path like "parent/subdir"
-                    full_path = "/".join(parts[:-1])  # Remove README.md
-                    # Check if this exact path is in allowlist
-                    if full_path in allowlist_entries:
-                        # This is a sub-entry with its own entry -> use .qmd
-                        target_output = f"{full_path}.qmd"
-                    elif parts[0] == ".":
-                        # ./subdir/README.md -> check if subdir has own entry
-                        subdir = parts[1]
-                        if subdir in parent_index_only:
-                            target_output = f"{subdir}/index.qmd"
-                        else:
-                            target_output = f"{subdir}.qmd"
-                    else:
-                        # parent/subdir where parent doesn't have own entry
-                        target_output = f"{full_path}/index.qmd"
-            else:
-                # Regular .md file -> convert to .qmd, keep path structure
-                target_output = "/".join(parts)[:-2] + "qmd"
-
-            # Compute relative path from current output file to target
-            current_parts = current_output_path.split("/")
-            target_parts = target_output.split("/")
-
-            # Special case: if current is a subdir file and target is a single-component file at root
-            # Example: current="magistral/vision", target="magistral.qmd"
-            if len(current_parts) > 1 and len(target_parts) == 1:
-                # Current is in subdir, target is at root level
-                # Go up to root: ../ for each level
-                up_count = len(current_parts) - 1
-                rel_parts = [".."] * up_count + [target_parts[0]]
-                new_url = "/".join(rel_parts)
-            else:
-                # Find common prefix
-                i = 0
-                while (
-                    i < min(len(current_parts) - 1, len(target_parts))
-                    and current_parts[i] == target_parts[i]
-                ):
-                    i += 1
-
-                # Build relative path: go up (../) then down to target
-                up_count = len(current_parts) - 1 - i
-                rel_parts = [".."] * up_count + target_parts[i:]
-
-                if not rel_parts or rel_parts == [".."]:
-                    # Points to same directory or parent
-                    new_url = "/".join(rel_parts) if rel_parts else "."
-                else:
-                    new_url = "/".join(rel_parts)
-
-            return f"[{text}]({new_url})"
-        except (ValueError, IndexError):
-            return m.group(0)
-
-    return LINK_RE.sub(repl, md)
-
-
-def write_qmd(out_path: Path, title: str, body_md: str):
-    out_path.parent.mkdir(parents=True, exist_ok=True)
-    fm = f"---\ntitle: {title!r}\nexecute:\n  eval: false\nformat:\n  html:\n    toc: true\n---\n\n"
-    out_path.write_text(fm + body_md, encoding="utf-8")
-
-
-def update_quarto_yml(generated: list[tuple[str, str, str]]):
-    """
-    Update _quarto.yml with the generated example files in the correct order.
-    This keeps the sidebar in sync with the allowlist.
-
-    Model Guides is now nested under "Getting Started" section.
-    Creates nested sections for models with sub-entries (e.g., magistral, ministral3).
-    Parent pages are now flat files (e.g., ministral3.qmd) with sub-pages in subdirs.
-    """
-    quarto_yml = ROOT / "_quarto.yml"
-    if not quarto_yml.exists():
-        print(f"[WARN] {quarto_yml} not found, skipping update", file=sys.stderr)
-        return
-
-    content = quarto_yml.read_text(encoding="utf-8")
-
-    # First pass: find all parents that have sub-entries
-    parents_with_subs = set()
-    for path, _name, _title in generated:
-        if "/" in path:
-            parent = path.split("/")[0]
-            parents_with_subs.add(parent)
-
-    # Build the YAML contents while preserving allowlist order
-    lines = []
-    processed_sections = set()
-
-    for path, _name, title in generated:
-        # Check if this is a parent page that has sub-pages
-        if path in parents_with_subs:
-            # This is a parent page with sub-pages - create a nested section
-            if path not in processed_sections:
-                processed_sections.add(path)
-                section_title = (
-                    title or path.replace("-", " ").replace("_", " ").title()
-                )
-                lines.append(f'                - section: "{section_title}"')
-                lines.append("                  contents:")
-                # Add the parent page first
-                lines.append(f"                    - docs/models/{path}.qmd")
-                # Then add all sub-pages
-                for sub_path, _sub_name, _sub_title in generated:
-                    if "/" in sub_path and sub_path.split("/")[0] == path:
-                        lines.append(
-                            f"                    - docs/models/{sub_path}.qmd"
-                        )
-        elif "/" not in path:
-            # This is a flat item with no sub-pages
-            # Skip if it was already included as part of a parent section
-            if path not in processed_sections:
-                lines.append(f"                - docs/models/{path}.qmd")
-
-    yaml_content = "\n".join(lines) + "\n"
-
-    # Pattern to match only the Model Guides contents, stopping at the next item
-    # in Getting Started (lines starting with 12 spaces: same level as the section)
-    pattern = r'(            - section: "Model Guides"\n              contents:)([^\n]*|.*?)(?=\n            - |\n        - section:|\n\nformat:)'
-
-    def replacement(match):
-        prefix = match.group(1)
-        return prefix + "\n" + yaml_content
-
-    new_content = re.sub(pattern, replacement, content, flags=re.DOTALL)
-
-    if new_content != content:
-        quarto_yml.write_text(new_content, encoding="utf-8")
-        print(f"Updated {quarto_yml}")
-    else:
-        print(f"No changes needed for {quarto_yml}")
-
-
-def main():
-    allow = read_allowlist()
-    if not EXAMPLES_DIR.exists():
-        print(f"[WARN] {EXAMPLES_DIR} not found", file=sys.stderr)
-        return
-
-    (OUTPUT_DIR / "assets").mkdir(parents=True, exist_ok=True)
-
-    # First pass: identify which parents have their own entry vs only sub-entries
-    parent_entries = set()  # Parents that have their own entry
-    parent_with_subs = set()  # Parents that have sub-entries
-    allowlist_entries = set()  # All entries in allowlist
-
-    for item in allow:
-        if isinstance(item, str):
-            name = item
-        else:
-            name = item.get("name")
-
-        allowlist_entries.add(name)
-
-        if "/" in name:
-            parent = name.split("/")[0]
-            parent_with_subs.add(parent)
-        else:
-            parent_entries.add(name)
-
-    # Parents with subs that DON'T have their own entry -> use index.qmd
-    parent_index_only = parent_with_subs - parent_entries
-
-    generated = []
-    seen_dirs = set()  # Track which parent directories we've created index for
-
-    for item in allow:
-        if isinstance(item, str):
-            name = item
-            title = None
-        else:
-            name = item.get("name")
-            title = item.get("title")
-
-        if not name:
-            print(f"[WARN] Skipping item without name: {item}", file=sys.stderr)
-            continue
-
-        src_dir = EXAMPLES_DIR / name
-        if not src_dir.exists() or not src_dir.is_dir():
-            print(f"[WARN] Skipping {name} (not a directory)", file=sys.stderr)
-            continue
-
-        readme = find_readme(src_dir)
-        if not readme:
-            print(f"[WARN] Skipping {name} (no README.md)", file=sys.stderr)
-            continue
-
-        md = readme.read_text(encoding="utf-8")
-
-        # Determine output path first (needed for link rewriting)
-        parts = name.split("/")
-        if len(parts) == 1:
-            # Simple case: no subdirectory
-            out_path = OUTPUT_DIR / f"{parts[0]}.qmd"
-            sidebar_path = parts[0]
-        else:
-            # Has subdirectory: e.g., magistral/think
-            parent = parts[0]
-            child = "-".join(parts[1:])  # handle nested subdirs
-            out_path = OUTPUT_DIR / parent / f"{child}.qmd"
-            sidebar_path = f"{parent}/{child}"
-
-        # Remove the first H1 (we use frontmatter title instead)
-        md, _ = remove_first_h1(md)
-        # Rewrite links between README files
-        md = rewrite_readme_links(
-            md,
-            src_dir,
-            EXAMPLES_DIR,
-            parent_index_only,
-            name,
-            allowlist_entries,
-            sidebar_path,
-        )
-        md = rewrite_and_copy_assets(md, src_dir, OUTPUT_DIR)
-
-        # Handle parent page generation for sub-entries
-        if len(parts) > 1:
-            # Has subdirectory: e.g., magistral/think
-            parent = parts[0]
-
-            # Create parent.qmd if not already done and parent doesn't have own entry
-            if parent not in seen_dirs and parent in parent_index_only:
-                parent_readme = find_readme(EXAMPLES_DIR / parent)
-                if parent_readme:
-                    parent_md = parent_readme.read_text(encoding="utf-8")
-                    parent_md, _ = remove_first_h1(parent_md)
-                    parent_md = rewrite_readme_links(
-                        parent_md,
-                        EXAMPLES_DIR / parent,
-                        EXAMPLES_DIR,
-                        parent_index_only,
-                        parent,
-                        allowlist_entries,
-                        parent,
-                    )
-                    parent_md = rewrite_and_copy_assets(
-                        parent_md, EXAMPLES_DIR / parent, OUTPUT_DIR
-                    )
-                    parent_title = parent.replace("-", " ").replace("_", " ").title()
-                    write_qmd(OUTPUT_DIR / f"{parent}.qmd", parent_title, parent_md)
-                    generated.append((parent, parent, parent_title))
-                    seen_dirs.add(parent)
-
-        if not title:
-            title = name.replace("/", " ").replace("-", " ").title()
-
-        write_qmd(out_path, title, md)
-        generated.append((sidebar_path, name, title))
-
-    # Index page - preserve allowlist order
-    if generated:
-        listing = "\n".join(
-            [f"- [{title}]({path}.qmd)" for path, name, title in generated]
-        )
-        index_md = (
-            "# Model Guides\n\nBelow are the curated examples for training various model architectures:\n\n"
-            + listing
-            + "\n"
-        )
-        index_fm = (
-            "---\nexecute:\n  eval: false\nformat:\n  html:\n    toc: true\n---\n\n"
-        )
-        (OUTPUT_DIR / "index.qmd").write_text(index_fm + index_md, encoding="utf-8")
-
-        # Auto-update _quarto.yml to keep sidebar in sync
-        update_quarto_yml(generated)
-
-
-if __name__ == "__main__":
-    main()
--- a/docs/sequence_parallelism.qmd
+++ b/docs/sequence_parallelism.qmd
@@ -49,9 +49,9 @@ When sequence parallelism is enabled:
 To use sequence parallelism, you need:

 - Multiple GPUs (at least 2)
- The `ring-flash-attn` package. Install with:
-  - `pip install axolotl[ring-flash-attn]` (preferred)
-  - `pip install ring-flash-attn>=0.1.4`
+- The `ring-flash-attn` package. Install with either `uv sync --extra ring-flash-attn`
+  (from a cloned repository) or `uv pip install ring-flash-attn>=0.1.4`.
+- Flash Attention installed separately with `uv pip install flash-attn --no-build-isolation`.

 ## Limitations

--- a/docs/telemetry.qmd
+++ b/docs/telemetry.qmd
@@ -1,61 +0,0 @@
---
-title: Telemetry
-description: A description of the telemetry implementation in Axolotl.
---
-
-# Telemetry in Axolotl
-
-Axolotl implements anonymous telemetry to help maintainers understand how the library
-is used and where users encounter issues. This data helps prioritize features, optimize
-performance, and fix bugs.
-
-## Data Collection
-
-We collect:
-
- System info: OS, Python version, Axolotl version, PyTorch version, Transformers
-version, etc.
- Hardware info: CPU count, memory, GPU count and models
- Runtime metrics: Training progress, memory usage, timing information
- Usage patterns: Models (from a whitelist) and configurations used
- Error tracking: Stack traces and error messages (sanitized to remove personal
-information)
-
-Personally identifiable information (PII) is not collected.
-
-## Implementation
-
-Telemetry is implemented using PostHog and consists of:
-
- `axolotl.telemetry.TelemetryManager`: A singleton class that initializes the
-telemetry system and provides methods for tracking events.
- `axolotl.telemetry.errors.send_errors`: A decorator that captures exceptions and
-sends sanitized stack traces.
- `axolotl.telemetry.runtime_metrics.RuntimeMetricsTracker`: A class that tracks
-runtime metrics during training.
- `axolotl.telemetry.callbacks.TelemetryCallback`: A Trainer callback that sends
-runtime metrics telemetry.
-
-The telemetry system will block training startup for 10 seconds to ensure users are
-aware of data collection, unless telemetry is explicitly enabled or disabled.
-
-## Opt-Out Mechanism
-
-Telemetry is **enabled by default** on an opt-out basis. To disable it, set
-`AXOLOTL_DO_NOT_TRACK=1` or `DO_NOT_TRACK=1`.
-
-A warning message will be logged on start to clearly inform users about telemetry.
-We will remove this after some period.
-
-To hide the warning message about telemetry that is displayed on train, etc. startup,
-explicitly set: `AXOLOTL_DO_NOT_TRACK=0` (enable telemetry) or `AXOLOTL_DO_NOT_TRACK=1`
-(explicitly disable telemetry).
-
-## Privacy
-
- All path-like config information is automatically redacted from telemetry data
- Model information is only collected for whitelisted organizations
-    - See `axolotl/telemetry/whitelist.yaml` for the set of whitelisted organizations
- Each run generates a unique anonymous ID
-    - This allows us to link different telemetry events in a single same training run
- Telemetry is only sent from the main process to avoid duplicate events
--- a/examples/LiquidAI/README.md
+++ b/examples/LiquidAI/README.md
@@ -6,17 +6,20 @@ LFM2 features a new hybrid Liquid architecture with multiplicative gates, short-

 This guide shows how to fine-tune both the LFM2 and LFM2-VL models with Axolotl.

-Thanks to the team at LiquidAI for giving us early access to prepare for these releases.
-
 ## Getting Started

 1.  Install Axolotl following the [installation guide](https://docs.axolotl.ai/docs/installation.html).

    Here is an example of how to install from pip:
    ```bash
-    # Ensure you have a compatible version of Pytorch installed
-    pip3 install packaging setuptools wheel ninja
-    pip3 install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
+    # Ensure you have a compatible version of PyTorch installed
+    # Option A: manage dependencies in your project
+    uv add 'axolotl>=0.12.0'
+    uv pip install flash-attn --no-build-isolation
+
+    # Option B: quick install
+    uv pip install 'axolotl>=0.12.0'
+    uv pip install flash-attn --no-build-isolation
    ```

 2.  Run one of the finetuning examples below.
@@ -33,19 +36,11 @@ Thanks to the team at LiquidAI for giving us early access to prepare for these r
    axolotl train examples/LiquidAI/lfm2-vl-lora.yaml
    ```

-    **LFM2-MoE**
-    ```bash
-    pip install git+https://github.com/huggingface/transformers.git@0c9a72e4576fe4c84077f066e585129c97bfd4e6
-
-    # LoRA SFT (1x48GB @ 16.2GiB)
-    axolotl train examples/LiquidAI/lfm2-8b-a1b-lora.yaml
-    ```
-
 ### TIPS

 - **Installation Error**: If you encounter `ImportError: ... undefined symbol ...` or `ModuleNotFoundError: No module named 'causal_conv1d_cuda'`, the `causal-conv1d` package may have been installed incorrectly. Try uninstalling it:
  ```bash
-  pip uninstall -y causal-conv1d
+  uv pip uninstall -y causal-conv1d
  ```

 - **Dataset Loading**: Read more on how to load your own dataset in our [documentation](https://docs.axolotl.ai/docs/dataset_loading.html).
@@ -55,13 +50,14 @@ Thanks to the team at LiquidAI for giving us early access to prepare for these r

 ## Optimization Guides

- [Optimizations Guide](https://docs.axolotl.ai/docs/optimizations.html)
+- [Multi-GPU Training](https://docs.axolotl.ai/docs/multi-gpu.html)
+- [LoRA Optimizations](https://docs.axolotl.ai/docs/lora_optims.html)
+- [Multi-Node Training](https://docs.axolotl.ai/docs/multi-node.html)

 ## Related Resources

 - [LFM2 Blog](https://www.liquid.ai/blog/liquid-foundation-models-v2-our-second-series-of-generative-ai-models)
 - [LFM2-VL Blog](https://www.liquid.ai/blog/lfm2-vl-efficient-vision-language-models)
- [LFM2-MoE Blog](https://www.liquid.ai/blog/lfm2-8b-a1b-an-efficient-on-device-mixture-of-experts)
 - [Axolotl Docs](https://docs.axolotl.ai)
 - [Axolotl GitHub](https://github.com/axolotl-ai-cloud/axolotl)
 - [Axolotl Discord](https://discord.gg/7m9sfhzaf3)
--- a/examples/LiquidAI/lfm2-350m-fft.yaml
+++ b/examples/LiquidAI/lfm2-350m-fft.yaml
@@ -1,7 +1,6 @@
 base_model: LiquidAI/LFM2-350M

-plugins:
-  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+chunked_cross_entropy: true

 eot_tokens:
  - "<|im_end|>"
--- a/examples/LiquidAI/lfm2-8b-a1b-lora.yaml
+++ b/examples/LiquidAI/lfm2-8b-a1b-lora.yaml
@@ -1,59 +0,0 @@
-base_model: LiquidAI/LFM2-8B-A1B
-
-plugins:
-  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
-
-load_in_8bit: true
-
-eot_tokens:
-  - "<|im_end|>"
-datasets:
-  - path: mlabonne/FineTome-100k
-    type: chat_template
-    split: train[:20%]
-    field_messages: conversations
-    message_field_role: from
-    message_field_content: value
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.05
-output_dir: ./outputs/out
-
-sequence_len: 4096
-sample_packing: true
-
-adapter: lora
-lora_model_dir:
-
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules: 'model.layers.[\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj'
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 2
-micro_batch_size: 4
-num_epochs: 1
-optimizer: adamw_torch_fused
-lr_scheduler: cosine
-learning_rate: 5e-5
-
-bf16: true
-tf32: true
-
-gradient_checkpointing: true
-resume_from_checkpoint:
-logging_steps: 1
-flash_attention: true
-
-warmup_ratio: 0.1
-evals_per_epoch: 2
-saves_per_epoch: 1
-
-weight_decay: 0.0
-
-# save_first_step: true  # uncomment this to validate checkpoint saving works with your config
--- a/examples/LiquidAI/lfm2-vl-lora.yaml
+++ b/examples/LiquidAI/lfm2-vl-lora.yaml
@@ -3,9 +3,6 @@ trust_remote_code: true
 model_type: AutoModelForImageTextToText
 processor_type: AutoProcessor

-plugins:
-  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
-
 # these 3 lines are needed for now to handle vision chat templates w images
 skip_prepare_dataset: true
 remove_unused_columns: false
--- a/examples/apertus/README.md
+++ b/examples/apertus/README.md
@@ -15,8 +15,8 @@ This guide shows how to fine-tune it with Axolotl with multi-turn conversations
 git clone https://github.com/axolotl-ai-cloud/axolotl.git
 cd axolotl

-pip3 install packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation -e '.[flash-attn]'
+uv sync
+uv pip install flash-attn --no-build-isolation

 # Install CCE https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy
 python scripts/cutcrossentropy_install.py | sh
@@ -31,7 +31,7 @@ python scripts/cutcrossentropy_install.py | sh
 # For those using our Docker image, use the below path.
 export CUDA_HOME=/usr/local/cuda

-pip3 install git+https://github.com/nickjbrowning/XIELU@59d6031 --no-build-isolation --no-deps
+uv pip install git+https://github.com/nickjbrowning/XIELU@59d6031 --no-build-isolation --no-deps
 ```

 For any installation errors, see [XIELU Installation Issues](#xielu-installation-issues)
@@ -67,7 +67,7 @@ If those didn't help, please try the below solutions:
 1. Pass env for CMAKE and try install again:

    ```bash
-    Python_EXECUTABLE=$(which python) pip3 install git+https://github.com/nickjbrowning/XIELU@59d6031 --no-build-isolation --no-deps
+    Python_EXECUTABLE=$(which python) uv pip install git+https://github.com/nickjbrowning/XIELU@59d6031 --no-build-isolation --no-deps
    ```

 2. Git clone the repo and manually hardcode python path:
@@ -92,7 +92,7 @@ If those didn't help, please try the below solutions:
    ```

    ```bash
-    pip3 install . --no-build-isolation --no-deps
+    uv pip install . --no-build-isolation --no-deps
    ```

 ## Optimization Guides
--- a/examples/arcee/README.md
+++ b/examples/arcee/README.md
@@ -17,8 +17,8 @@ Thanks to the team at Arcee.ai for using Axolotl in supervised fine-tuning the A
 git clone https://github.com/axolotl-ai-cloud/axolotl.git
 cd axolotl

-pip3 install packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation -e '.[flash-attn]'
+uv sync
+uv pip install flash-attn --no-build-isolation

 # Install CCE https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy
 python scripts/cutcrossentropy_install.py | sh
--- a/examples/colab-notebooks/colab-axolotl-example.ipynb
+++ b/examples/colab-notebooks/colab-axolotl-example.ipynb
@@ -12,10 +12,10 @@
    "\n",
    "Axolotl is the most performant LLM post-training framework available, delivering faster training with efficient, consistent and stable performance. Train your workload and ship your product 30% faster; saving you both time and money.\n",
    "\n",
-    "- ⭐ us on [GitHub](https://github.com/axolotl-ai-cloud/axolotl)\n",
-    "- 📜 Read the [Docs](http://docs.axolotl.ai/)\n",
-    "- 💬 Chat with us on [Discord](https://discord.gg/mnpEYgRUmD)\n",
-    "- 📰 Get updates on [X/Twitter](https://x.com/axolotl_ai)\n"
+    "- \u2b50 us on [GitHub](https://github.com/axolotl-ai-cloud/axolotl)\n",
+    "- \ud83d\udcdc Read the [Docs](http://docs.axolotl.ai/)\n",
+    "- \ud83d\udcac Chat with us on [Discord](https://discord.gg/mnpEYgRUmD)\n",
+    "- \ud83d\udcf0 Get updates on [X/Twitter](https://x.com/axolotl_ai)\n"
   ]
  },
  {
@@ -39,8 +39,8 @@
   "source": [
    "%%capture\n",
    "# This step can take ~5-10 minutes to install dependencies\n",
-    "!pip install --no-build-isolation axolotl[flash-attn]>=0.9.1\n",
-    "!pip install \"cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@0d4ce4b\""
+    "!uv pip install --no-build-isolation axolotl>=0.9.1\n!uv pip install flash-attn --no-build-isolation\n",
+    "!uv pip install \"cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@147ea28\""
   ]
  },
  {
@@ -253,6 +253,7 @@
   "source": [
    "from axolotl.utils import set_pytorch_cuda_alloc_conf\n",
    "\n",
+    "# Set \"PYTORCH_CUDA_ALLOC_CONF\" env to save memory\n",
    "set_pytorch_cuda_alloc_conf()"
   ]
  },
@@ -1370,7 +1371,7 @@
       "version_minor": 0
      },
      "text/plain": [
-       "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
+       "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv\u2026"
      ]
     },
     "metadata": {},
@@ -1728,9 +1729,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_12815f401eba44658caa7b2e490137a8",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_30e02aa2d0d241979369e598287f2639",
-      "value": "Drop Samples with Zero Trainable Tokens (num_proc=2): 100%"
+      "value": "Drop\u2007Samples\u2007with\u2007Zero\u2007Trainable\u2007Tokens\u2007(num_proc=2):\u2007100%"
     }
    },
    "083f9cda8d754c168beee10d2f8955a2": {
@@ -1773,9 +1774,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_b195f160ca20442fadd8b5aed0ee41af",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_ca65e32eb52f48c09a84b33cb18f22cd",
-      "value": " 11.4M/11.4M [00:00&lt;00:00, 21.8MB/s]"
+      "value": "\u200711.4M/11.4M\u2007[00:00&lt;00:00,\u200721.8MB/s]"
     }
    },
    "0a46ad75c198463d843fb35e813642cb": {
@@ -1916,7 +1917,7 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_b1bea589efa14258a9982071b87938bf",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_590eef89881545aa8bbef9a8bbe7fb00",
      "value": "\n<b>Pro Tip:</b> If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. </center>"
     }
@@ -1937,9 +1938,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_bfcdbba993b74972a9e3e575f86908ff",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_6ebb2ec171414e47a14765505f64bb3c",
-      "value": " 3.84G/3.84G [00:09&lt;00:00, 664MB/s]"
+      "value": "\u20073.84G/3.84G\u2007[00:09&lt;00:00,\u2007664MB/s]"
     }
    },
    "0e936d9dbf9c4fdd86bbfe9730dedc47": {
@@ -2295,9 +2296,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_349eee9f56d64f0cba6fc24ff2c50c9b",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_7e5d3774060e4589aa65982da5ea4ef4",
-      "value": " 9985/9985 [00:04&lt;00:00, 2604.11 examples/s]"
+      "value": "\u20079985/9985\u2007[00:04&lt;00:00,\u20072604.11\u2007examples/s]"
     }
    },
    "16d1283741404b7bb319094c992fce01": {
@@ -2316,9 +2317,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_a4e5789584564049b83df7c6c54a3e08",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_ff3a94b146a948b6907f5d80c7157f99",
-      "value": " 9985/0 [00:00&lt;00:00, 50763.46 examples/s]"
+      "value": "\u20079985/0\u2007[00:00&lt;00:00,\u200750763.46\u2007examples/s]"
     }
    },
    "1811cda0644e4190a9469d1774435d82": {
@@ -2389,9 +2390,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_e366ae3fceec4566b9ed303d6c5f90af",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_5dd7d150dbe04f08b165ce7f2c27cd11",
-      "value": "model-00008-of-00008.safetensors: 100%"
+      "value": "model-00008-of-00008.safetensors:\u2007100%"
     }
    },
    "19127c7bb1554ccbac877059f9a82db0": {
@@ -2560,9 +2561,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_0dea5caa27384f5689e3cab51f558727",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_a6f48410b9964fefba0c3009a77dc838",
-      "value": " 9.68k/9.68k [00:00&lt;00:00, 812kB/s]"
+      "value": "\u20079.68k/9.68k\u2007[00:00&lt;00:00,\u2007812kB/s]"
     }
    },
    "1f7d30f71bbd4547a9150d21da071055": {
@@ -2633,9 +2634,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_f4a1795dc7514a718f478245f521f0ba",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_5e746eb25bbe416fb585fa24e79f5177",
-      "value": "model-00002-of-00008.safetensors: 100%"
+      "value": "model-00002-of-00008.safetensors:\u2007100%"
     }
    },
    "20352e5f58d24bb8b1f3940efd14fe4a": {
@@ -2706,9 +2707,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_1c6f1f10667545aaab958016ba7e2c94",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_e6e969610738449887259063967f82b0",
-      "value": " 2.78M/2.78M [00:00&lt;00:00, 17.8MB/s]"
+      "value": "\u20072.78M/2.78M\u2007[00:00&lt;00:00,\u200717.8MB/s]"
     }
    },
    "258b7c635c1045329d4669e48c46ccd5": {
@@ -3055,9 +3056,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_be724f04b03942b2a033a7e8898bb4fd",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_fcbab4d8dced41a18dfccce81e3a45a0",
-      "value": "model-00005-of-00008.safetensors: 100%"
+      "value": "model-00005-of-00008.safetensors:\u2007100%"
     }
    },
    "3036608c71904ce9ae4bb2a9fa8802d9": {
@@ -3076,9 +3077,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_5ca6be24acb548cea130bd58e9954c7c",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_5cfb02ee044b4011a378efa8b54a370f",
-      "value": " 3.96G/3.96G [00:10&lt;00:00, 531MB/s]"
+      "value": "\u20073.96G/3.96G\u2007[00:10&lt;00:00,\u2007531MB/s]"
     }
    },
    "30a81da86f8043eca301e86a8651201a": {
@@ -3628,9 +3629,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_8f5bd719974e41c3a8dd9a5b0d3d71e6",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_b87c84de30e84b3abf4871461fb9cbd3",
-      "value": "Loading checkpoint shards: 100%"
+      "value": "Loading\u2007checkpoint\u2007shards:\u2007100%"
     }
    },
    "41f3b32c2f6b4034ae7a3b9124e28bc7": {
@@ -3790,7 +3791,7 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_39789237703c4a418134243055c9cbf5",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_a3a945817f684328b34651fe052393ec",
      "value": "Connecting..."
     }
@@ -4076,9 +4077,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_4d468f96ec924681ad65eb671674b93e",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_ad7599de524549c48bf2d3124ad4b299",
-      "value": "Dropping Long Sequences (num_proc=2): 100%"
+      "value": "Dropping\u2007Long\u2007Sequences\u2007(num_proc=2):\u2007100%"
     }
    },
    "5ca240f31e6b44e3882c5eb37cd5a309": {
@@ -4470,9 +4471,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_5e18768f7ad6434ba8b8b8a2e853e204",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_bb33aec33a6447078c31bfd728942994",
-      "value": " 728/728 [00:00&lt;00:00, 20.3kB/s]"
+      "value": "\u2007728/728\u2007[00:00&lt;00:00,\u200720.3kB/s]"
     }
    },
    "62e302ebdad64aada0ffe64ae1c873f3": {
@@ -4635,9 +4636,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_81c3db71ac704280ad030072655f1537",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_042e091f75694c47aee761e760e76773",
-      "value": " 9985/9985 [00:02&lt;00:00, 3977.47 examples/s]"
+      "value": "\u20079985/9985\u2007[00:02&lt;00:00,\u20073977.47\u2007examples/s]"
     }
    },
    "67da6c4260574869aa24c3cbc1bc1654": {
@@ -4777,7 +4778,7 @@
      "description_tooltip": null,
      "disabled": false,
      "layout": "IPY_MODEL_2e257c8be2da40b4bb67a9e4ab6811f3",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_56e3768bef5a4b9db4168c5c17f509c2",
      "value": ""
     }
@@ -4822,9 +4823,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_41f3b32c2f6b4034ae7a3b9124e28bc7",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_a10d0a76010f4e508c65a9b69ebc5156",
-      "value": "Tokenizing Prompts (num_proc=2): 100%"
+      "value": "Tokenizing\u2007Prompts\u2007(num_proc=2):\u2007100%"
     }
    },
    "704f2f5a9b1c49d5a75a0025a5dda11b": {
@@ -5070,9 +5071,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_93a44a11aa4846fa8efc6c1413ef1627",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_a55060adc3564407ac81ad7297d34aaa",
-      "value": "train.jsonl: 100%"
+      "value": "train.jsonl:\u2007100%"
     }
    },
    "7be6f04c284e4326bb4ff3d301e7b3c6": {
@@ -5137,9 +5138,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_7fd44cf9ca6e4726bfd7ac21846d6a14",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_366a343b62fa47d8985a3bd464d99f9e",
-      "value": "config.json: 100%"
+      "value": "config.json:\u2007100%"
     }
    },
    "7cd0b85ebd204b7aba908417811ce4e0": {
@@ -5338,9 +5339,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_67da6c4260574869aa24c3cbc1bc1654",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_94b9088614464f60a203de39dbcae853",
-      "value": " 8/8 [01:47&lt;00:00, 11.64s/it]"
+      "value": "\u20078/8\u2007[01:47&lt;00:00,\u200711.64s/it]"
     }
    },
    "823f1c78f15043e38bbd4dca3932a86a": {
@@ -5487,7 +5488,7 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_8640ac440fbc4644b9a3af7ba3ae7183",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_5cea7996f02040b187ece0bb2d6a8d1f",
      "value": "<center> <img\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.svg\nalt='Hugging Face'> <br> Copy a token from <a\nhref=\"https://huggingface.co/settings/tokens\" target=\"_blank\">your Hugging Face\ntokens page</a> and paste it below. <br> Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file. </center>"
     }
@@ -5508,9 +5509,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_ef223e8504b64e3592589880326aaf41",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_598da69727bd4fb8b1caf465ac736d7a",
-      "value": " 1.67M/1.67M [00:00&lt;00:00, 19.0MB/s]"
+      "value": "\u20071.67M/1.67M\u2007[00:00&lt;00:00,\u200719.0MB/s]"
     }
    },
    "897b77a56c09479bb11d7f2a30997e55": {
@@ -5716,9 +5717,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_37de928300e34184881039378bd75e7f",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_0e936d9dbf9c4fdd86bbfe9730dedc47",
-      "value": " 3.96G/3.96G [00:13&lt;00:00, 273MB/s]"
+      "value": "\u20073.96G/3.96G\u2007[00:13&lt;00:00,\u2007273MB/s]"
     }
    },
    "936d04b5fe1b4c63bf0b080e423d051b": {
@@ -6049,9 +6050,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_d955dcaa0e944e719f3a06139dd54a03",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_d3de2662c7964f1ba96e58da382af720",
-      "value": "merges.txt: 100%"
+      "value": "merges.txt:\u2007100%"
     }
    },
    "9cd5211b5d8b457aa0002f1d17b80028": {
@@ -6070,9 +6071,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_6932489232ec4ab18a160b1e7fbcdfe1",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_4540927d98f54466b434ba4c0edf045d",
-      "value": "model-00007-of-00008.safetensors: 100%"
+      "value": "model-00007-of-00008.safetensors:\u2007100%"
     }
    },
    "9d4897eefb5f48259ffb2d23e332f752": {
@@ -6302,9 +6303,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_3aaecbf540f54a2db9ab0931e3b1fe57",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_9e333ed3b5014069ac1dd969255dd591",
-      "value": " 239/239 [00:00&lt;00:00, 30.9kB/s]"
+      "value": "\u2007239/239\u2007[00:00&lt;00:00,\u200730.9kB/s]"
     }
    },
    "a20927bf5f2c41f58c1e31ac858ab36c": {
@@ -6323,9 +6324,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_1811cda0644e4190a9469d1774435d82",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_35c811d2ae8e43f3b5cecbdd3cfa857f",
-      "value": "tokenizer.json: 100%"
+      "value": "tokenizer.json:\u2007100%"
     }
    },
    "a3a945817f684328b34651fe052393ec": {
@@ -6359,9 +6360,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_ed5ca967ad5342929e578ac6aa4dc4c0",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_af401d117d5047629d3a6e2361757b62",
-      "value": "model-00001-of-00008.safetensors: 100%"
+      "value": "model-00001-of-00008.safetensors:\u2007100%"
     }
    },
    "a4e5789584564049b83df7c6c54a3e08": {
@@ -6493,9 +6494,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_fa1282ccc7544e4f818e2f03ccffe4a5",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_bbbf575d2a4b4c6ea8389be79b2a6039",
-      "value": "model.safetensors.index.json: 100%"
+      "value": "model.safetensors.index.json:\u2007100%"
     }
    },
    "ab93eabd7cea4b94b4b7a387f101e8a1": {
@@ -6581,9 +6582,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_62e302ebdad64aada0ffe64ae1c873f3",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_bd1b0dfed6d34d16af33a4a58330f5ec",
-      "value": "Saving the dataset (1/1 shards): 100%"
+      "value": "Saving\u2007the\u2007dataset\u2007(1/1\u2007shards):\u2007100%"
     }
    },
    "ad7599de524549c48bf2d3124ad4b299": {
@@ -6966,9 +6967,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_2b3a2659b12244bd8548320320016dbf",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_0cd7efffbb3c4c4b972e63749f61ab97",
-      "value": "Generating train split: "
+      "value": "Generating\u2007train\u2007split:\u2007"
     }
    },
    "b87c84de30e84b3abf4871461fb9cbd3": {
@@ -7084,9 +7085,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_0f480e3a0b0a45d2a2d2dec3cad923f3",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_fcb30372e7404c5d8a1ad4df91e6c7b2",
-      "value": " 1.91G/1.91G [00:05&lt;00:00, 444MB/s]"
+      "value": "\u20071.91G/1.91G\u2007[00:05&lt;00:00,\u2007444MB/s]"
     }
    },
    "bd1b0dfed6d34d16af33a4a58330f5ec": {
@@ -7324,9 +7325,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_158c8b85dbf34de6a94b4e35e2fc7d5a",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_0b4c9753a7cb4354b8e5f187e6e1ad7c",
-      "value": " 3.96G/3.96G [00:15&lt;00:00, 564MB/s]"
+      "value": "\u20073.96G/3.96G\u2007[00:15&lt;00:00,\u2007564MB/s]"
     }
    },
    "c0991cf63ee6458b96e9a75e7a88b61a": {
@@ -7345,9 +7346,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_ed28e2e0410d4e0b855467e798e53d66",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_d93f134f802b4b69b575bdaf07dbd27c",
-      "value": "tokenizer_config.json: 100%"
+      "value": "tokenizer_config.json:\u2007100%"
     }
    },
    "c12ea43372ac4d57bb9605f1a429b397": {
@@ -7580,9 +7581,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_8bc9d8ba866c442b9118d9630009939c",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_9f56a2d9979c4bd8928c644c22c3ecdf",
-      "value": "model-00003-of-00008.safetensors: 100%"
+      "value": "model-00003-of-00008.safetensors:\u2007100%"
     }
    },
    "c6164e05a1914ae48083db9ad7f4ef7c": {
@@ -7693,9 +7694,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_e40d1c1ac9494b3bade9858324e7ffdf",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_d65b6b060d9845779299491ac5599c31",
-      "value": " 9985/9985 [01:04&lt;00:00, 189.08 examples/s]"
+      "value": "\u20079985/9985\u2007[01:04&lt;00:00,\u2007189.08\u2007examples/s]"
     }
    },
    "c7433acd3c4841e6958ae8f7e87b1808": {
@@ -7736,9 +7737,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_0077aedc3d174560bce924ee89e9c006",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_00321cce58884f6f9b3855a21fcd9187",
-      "value": "Add position_id column (Sample Packing) (num_proc=2): 100%"
+      "value": "Add\u2007position_id\u2007column\u2007(Sample\u2007Packing)\u2007(num_proc=2):\u2007100%"
     }
    },
    "ca65e32eb52f48c09a84b33cb18f22cd": {
@@ -8161,9 +8162,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_63580b6fb30642479fe3000915bf551a",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_8f726dbfb45d4528afa33e36a6313267",
-      "value": " 27.3M/27.3M [00:00&lt;00:00, 31.0MB/s]"
+      "value": "\u200727.3M/27.3M\u2007[00:00&lt;00:00,\u200731.0MB/s]"
     }
    },
    "d43c6df07ddb466587807d6dbe1ff614": {
@@ -8182,9 +8183,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_8c4d4fc5a30f4e7cb3be53fe2adda33d",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_e90658f4bcb642baa78426012f863152",
-      "value": "model-00004-of-00008.safetensors: 100%"
+      "value": "model-00004-of-00008.safetensors:\u2007100%"
     }
    },
    "d65b6b060d9845779299491ac5599c31": {
@@ -8473,9 +8474,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_34cf3df51fbc41cabfdbba153c007f0e",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_ac764024cf1c4e08ba7749afd2cd20ac",
-      "value": "vocab.json: 100%"
+      "value": "vocab.json:\u2007100%"
     }
    },
    "dfd2a2649b8341ef913207526708aff1": {
@@ -8668,9 +8669,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_c6164e05a1914ae48083db9ad7f4ef7c",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_813621384dc748b0ad06775e22761c0b",
-      "value": " 9985/9985 [00:03&lt;00:00, 3622.89 examples/s]"
+      "value": "\u20079985/9985\u2007[00:03&lt;00:00,\u20073622.89\u2007examples/s]"
     }
    },
    "e400cbf14bcc446a9d33b210cd93550b": {
@@ -9064,9 +9065,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_fba7aa824b38467ab3061b226114cdec",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_f3075dccbd2747b4a7913b66f44f2596",
-      "value": " 3.96G/3.96G [00:13&lt;00:00, 398MB/s]"
+      "value": "\u20073.96G/3.96G\u2007[00:13&lt;00:00,\u2007398MB/s]"
     }
    },
    "ec030fc3c346426f9abc3a89892258d3": {
@@ -9109,9 +9110,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_936d04b5fe1b4c63bf0b080e423d051b",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_f1cef8e8dc2646fb9fd09f3b09081074",
-      "value": " 36.5k/36.5k [00:00&lt;00:00, 4.32MB/s]"
+      "value": "\u200736.5k/36.5k\u2007[00:00&lt;00:00,\u20074.32MB/s]"
     }
    },
    "ed28e2e0410d4e0b855467e798e53d66": {
@@ -9421,9 +9422,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_735d4f225b24414294fc1b213c61223c",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_5e5e15b0569b474c9620083b3ec6af55",
-      "value": "generation_config.json: 100%"
+      "value": "generation_config.json:\u2007100%"
     }
    },
    "f4667818b9d34a09891cd727a429a610": {
@@ -9442,9 +9443,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_4b27c267393640f28f6eae0875bd2ed9",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_9858cb74a09748a39e8149baac96702c",
-      "value": " 3.96G/3.96G [00:11&lt;00:00, 457MB/s]"
+      "value": "\u20073.96G/3.96G\u2007[00:11&lt;00:00,\u2007457MB/s]"
     }
    },
    "f4a1795dc7514a718f478245f521f0ba": {
@@ -9829,9 +9830,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_d1f9b10c130542f094c8fd3d1e23b5e9",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_e575d87a7efe4ec7b1efde489839d4a6",
-      "value": "model-00006-of-00008.safetensors: 100%"
+      "value": "model-00006-of-00008.safetensors:\u2007100%"
     }
    },
    "fe18bba7f3fb4c31bf840541f36b3425": {
@@ -9872,9 +9873,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_e5a82df528bb4e408797a3b6c2758f4a",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_f113ebd8c1c34806bea4dd7ed3035173",
-      "value": " 9985/9985 [00:00&lt;00:00, 44264.88 examples/s]"
+      "value": "\u20079985/9985\u2007[00:00&lt;00:00,\u200744264.88\u2007examples/s]"
     }
    },
    "fea1b70fb46745feb5111b3929175b5d": {
@@ -9930,9 +9931,9 @@
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_ab93eabd7cea4b94b4b7a387f101e8a1",
-      "placeholder": "",
+      "placeholder": "\u200b",
      "style": "IPY_MODEL_704f2f5a9b1c49d5a75a0025a5dda11b",
-      "value": " 3.96G/3.96G [00:12&lt;00:00, 656MB/s]"
+      "value": "\u20073.96G/3.96G\u2007[00:12&lt;00:00,\u2007656MB/s]"
     }
    }
   }
--- a/examples/devstral/README.md
+++ b/examples/devstral/README.md
@@ -16,8 +16,13 @@ Thanks to the team at MistralAI for giving us early access to prepare for this r

 ```bash
 # Ensure you have Pytorch installed (Pytorch 2.6.0 min)
-pip3 install packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
+# Option A: manage dependencies in your project
+uv add 'axolotl>=0.12.0'
+uv pip install flash-attn --no-build-isolation
+
+# Option B: quick install
+uv pip install 'axolotl>=0.12.0'
+uv pip install flash-attn --no-build-isolation
 ```

 2. Install [Cut Cross Entropy](https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy) to reduce training VRAM usage
--- a/examples/devstral/devstral-small-qlora.yml
+++ b/examples/devstral/devstral-small-qlora.yml
@@ -52,7 +52,6 @@ gradient_checkpointing: true
 resume_from_checkpoint:
 logging_steps: 1
 flash_attention: true
-scaling_softmax: true

 loss_watchdog_threshold: 5.0
 loss_watchdog_patience: 3
--- a/examples/eaft/eaft-example.yml
+++ b/examples/eaft/eaft-example.yml
@@ -1,77 +0,0 @@
-base_model: google/gemma-3-1b-it
-
-model_type: Gemma3ForCausalLM
-cls_model_config: Gemma3TextConfig
-
-# gemma3 doesn't seem to play nice with ddp
-ddp_find_unused_parameters: true
-
-chat_template: gemma3
-eot_tokens:
-  - <end_of_turn>
-
-load_in_8bit: false
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: cgato/SlimOrcaDedupCleaned
-    type: chat_template
-    field_messages: conversations
-    message_property_mappings:
-      role: from
-      content: value
-
-dataset_prepared_path:
-val_set_size: 0
-output_dir: ./outputs/eaft-gemma-3-1b
-
-use_eaft: true
-eaft_alpha: 1.0
-eaft_k: 20
-
-sequence_len: 1024
-sample_packing: false
-
-adapter:
-lora_model_dir:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 1
-eval_batch_size: 1
-max_steps: 1000
-evaluation_strategy: "no"
-optimizer: adamw_torch_fused
-lr_scheduler: cosine
-learning_rate: 5e-5
-
-train_on_inputs: false
-group_by_length: false
-bf16: auto
-fp16:
-tf32: true
-
-gradient_checkpointing: true
-gradient_checkpointing_kwargs:
-  use_reentrant: false
-
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_ratio: 0.1
-weight_decay: 0.0
-debug:
-deepspeed:
-fsdp:
-fsdp_config:
-special_tokens:
--- a/examples/gemma3/gemma-3-1b-qlora.yml
+++ b/examples/gemma3/gemma-3-1b-qlora.yml
@@ -1,8 +1,7 @@
 base_model: google/gemma-3-1b-it
-
-model_type: Gemma3ForCausalLM
-cls_model_config: Gemma3TextConfig
-
+# optionally might have model_type or tokenizer_type
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name

@@ -30,7 +29,7 @@ output_dir: ./outputs/out
 adapter: qlora
 lora_r: 32
 lora_alpha: 16
-lora_dropout: 0
+lora_dropout: 0.05
 lora_target_linear: true

 sequence_len: 2048
--- a/examples/gemma3/gemma-3-270m-qlora.yml
+++ b/examples/gemma3/gemma-3-270m-qlora.yml
@@ -1,8 +1,7 @@
 base_model: google/gemma-3-270m-it
-
-model_type: Gemma3ForCausalLM
-cls_model_config: Gemma3TextConfig
-
+# optionally might have model_type or tokenizer_type
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name

@@ -30,7 +29,7 @@ output_dir: ./outputs/out
 adapter: qlora
 lora_r: 32
 lora_alpha: 16
-lora_dropout: 0
+lora_dropout: 0.05
 lora_target_linear: true

 sequence_len: 2048
--- a/examples/gemma3/gemma-3-4b-qlora.yml
+++ b/examples/gemma3/gemma-3-4b-qlora.yml
@@ -1,9 +1,5 @@
 base_model: google/gemma-3-4b-it

-# Need to set else transformers tries to load vision too
-model_type: Gemma3ForCausalLM
-cls_model_config: Gemma3TextConfig
-
 load_in_4bit: true

 # gemma3 doesn't seem to play nice with ddp
@@ -33,8 +29,8 @@ sample_packing: true

 lora_r: 32
 lora_alpha: 16
-lora_dropout: 0
-lora_target_linear: true
+lora_dropout: 0.05
+lora_target_modules: 'model.language_model.layers.[\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj'

 wandb_project:
 wandb_entity:
--- a/examples/gemma3/gemma-3-4b-vision-qlora.yml
+++ b/examples/gemma3/gemma-3-4b-vision-qlora.yml
@@ -31,7 +31,7 @@ pad_to_sequence_len: false

 lora_r: 32
 lora_alpha: 16
-lora_dropout: 0
+lora_dropout: 0.05
 lora_target_modules: 'model.language_model.layers.[\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj'

 wandb_project:
--- a/examples/gemma3n/README.md
+++ b/examples/gemma3n/README.md
@@ -10,17 +10,22 @@ Gemma-3n is a family of multimodal models from Google found on [HuggingFace](htt

 ```bash
 # Ensure you have Pytorch installed (Pytorch 2.6.0 min)
-pip3 install packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
+# Option A: manage dependencies in your project
+uv add 'axolotl>=0.12.0'
+uv pip install flash-attn --no-build-isolation
+
+# Option B: quick install
+uv pip install 'axolotl>=0.12.0'
+uv pip install flash-attn --no-build-isolation
 ```

 2. In addition to Axolotl's requirements, Gemma-3n requires:

 ```bash
-pip3 install timm==1.0.17
+uv pip install timm==1.0.17

 # for loading audio data
-pip3 install librosa==0.11.0
+uv pip install librosa==0.11.0
 ```

 3. Download sample dataset files
--- a/examples/glm46v/README.md
+++ b/examples/glm46v/README.md
@@ -1,44 +0,0 @@
-# Finetune GLM-4.6V with Axolotl
-
-GLM-4.6V is a family of vision-language models from ZhipuAI found on [HuggingFace](https://huggingface.co/zai-org/GLM-4.6V). This guide shows how to fine-tune it with Axolotl for vision-language tasks.
-
-
-
-## Getting started
-
-1. Install Axolotl from source following the [installation guide](https://docs.axolotl.ai/docs/installation.html#sec-edge-build).
-
-2. Install [Cut Cross Entropy](https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy) to reduce training VRAM usage.
-
-
-3. Run the fine-tuning:
-
-    glm-4-6v-flash(9B)
-    ```bash
-    axolotl train examples/glm46v/glm-4-6v-flash-qlora.yaml
-    ```
-
-Let us know how it goes. Happy finetuning! 🚀
-
-## Tips
-
- Vision datasets should follow the format described in the [multimodal docs](https://docs.axolotl.ai/docs/multimodal.html#dataset-format)
- You can run a **full finetuning** by removing the `adapter: qlora` and `load_in_4bit: true` from the config.
- Read more on how to load your own dataset in the [dataset loading docs](https://docs.axolotl.ai/docs/dataset_loading.html).
-
-## Supported Models
-
- **GLM-4.6V**: Full vision-language model (`zai-org/GLM-4.6V`)
- **GLM-4.6V-Flash**: Faster variant (`zai-org/GLM-4.6V-Flash`)
-
-## Optimization Guides
-
-Please check the [Optimizations doc](https://docs.axolotl.ai/docs/optimizations.html).
-
-## Related Resources
-
- [ZhipuAI GLM-4.6V](https://huggingface.co/zai-org/GLM-4.6V)
- [Axolotl Docs](https://docs.axolotl.ai)
- [Axolotl Website](https://axolotl.ai)
- [Axolotl GitHub](https://github.com/axolotl-ai-cloud/axolotl)
- [Axolotl Discord](https://discord.gg/7m9sfhzaf3)
--- a/examples/glm46v/glm-4-6v-flash-ddp.yaml
+++ b/examples/glm46v/glm-4-6v-flash-ddp.yaml
@@ -1,53 +0,0 @@
-base_model: zai-org/GLM-4.6V-Flash
-trust_remote_code: true
-
-processor_type: AutoProcessor
-load_in_4bit: true
-
-# these 3 lines are needed for now to handle vision chat templates w images
-skip_prepare_dataset: true
-remove_unused_columns: false
-sample_packing: false
-ddp_find_unused_parameters: true
-
-output_dir: ./outputs/glm-4-6v-flash-qlora
-datasets:
-  - path: HuggingFaceH4/llava-instruct-mix-vsft
-    type: chat_template
-    split: train[:1%]
-
-adapter: qlora
-lora_r: 16
-lora_alpha: 32
-lora_dropout: 0.05
-lora_target_modules:
-  - gate_proj
-  - down_proj
-  - up_proj
-  - q_proj
-  - v_proj
-  - k_proj
-  - o_proj
-
-sequence_len: 2048
-
-gradient_accumulation_steps: 4
-micro_batch_size: 1
-num_epochs: 1
-optimizer: adamw_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-bf16: auto
-tf32: false
-
-gradient_checkpointing: true
-gradient_checkpointing_kwargs:
-  use_reentrant: false
-logging_steps: 1
-sdp_attention: true
-
-warmup_ratio: 0.1
-evals_per_epoch: 0
-saves_per_epoch: 1
-weight_decay: 0.0
--- a/examples/glm46v/glm-4-6v-flash-qlora.yaml
+++ b/examples/glm46v/glm-4-6v-flash-qlora.yaml
@@ -1,50 +0,0 @@
-base_model: zai-org/GLM-4.6V-Flash
-trust_remote_code: true
-
-processor_type: AutoProcessor
-load_in_4bit: true
-
-# these 3 lines are needed for now to handle vision chat templates w images
-skip_prepare_dataset: true
-remove_unused_columns: false
-sample_packing: false
-
-output_dir: ./outputs/glm-4-6v-flash-qlora
-datasets:
-  - path: HuggingFaceH4/llava-instruct-mix-vsft
-    type: chat_template
-    split: train[:1%]
-
-adapter: qlora
-lora_r: 16
-lora_alpha: 32
-lora_dropout: 0.05
-lora_target_modules:
-  - gate_proj
-  - down_proj
-  - up_proj
-  - q_proj
-  - v_proj
-  - k_proj
-  - o_proj
-
-sequence_len: 2048
-
-gradient_accumulation_steps: 4
-micro_batch_size: 1
-num_epochs: 1
-optimizer: adamw_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-bf16: auto
-tf32: false
-
-gradient_checkpointing: true
-logging_steps: 1
-sdp_attention: true
-
-warmup_ratio: 0.1
-evals_per_epoch: 0
-saves_per_epoch: 1
-weight_decay: 0.0
--- a/examples/gpt-oss/README.md
+++ b/examples/gpt-oss/README.md
@@ -2,8 +2,6 @@

 [GPT-OSS](https://huggingface.co/collections/openai/gpt-oss-68911959590a1634ba11c7a4) are a family of open-weight MoE models trained by OpenAI, released in August 2025. There are two variants: 20B and 120B.

-In October 2025, OpenAI released safeguard models built upon GPT-OSS called [GPT-OSS-Safeguard](https://huggingface.co/collections/openai/gpt-oss-safeguard). They use the same architecture, so the same examples below can be re-used.
-
 This guide shows how to fine-tune it with Axolotl with multi-turn conversations and proper masking.

 ## Getting started
@@ -14,8 +12,13 @@ This guide shows how to fine-tune it with Axolotl with multi-turn conversations

 ```bash
 # Ensure you have Pytorch installed (Pytorch 2.6.0 min)
-pip3 install packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
+# Option A: manage dependencies in your project
+uv add 'axolotl>=0.12.0'
+uv pip install flash-attn --no-build-isolation
+
+# Option B: quick install
+uv pip install 'axolotl>=0.12.0'
+uv pip install flash-attn --no-build-isolation
 ```

 2. Choose one of the following configs below for training the 20B model. (for 120B, see [below](#training-120b))
@@ -66,16 +69,6 @@ axolotl merge-sharded-fsdp-weights examples/gpt-oss/gpt-oss-120b-fft-fsdp2-offlo
 mv ./outputs/gpt-oss-out/merged/* ./outputs/gpt-oss-out/
 ```

-### How to set reasoning_effort in template?
-
-The harmony template has a feature to set the `reasoning_effort` during prompt building. The default is `medium`. If you would like to adjust this, you can add the following to your config:
-
-```yaml
-chat_template_kwargs:
-  reasoning_effort: "high"  # low | medium | high
-```
-
-Currently, this applies globally. There is no method to apply per sample yet. If you are interested in adding this, please feel free to create an Issue to discuss.

 ### Inferencing your fine-tuned model

@@ -87,7 +80,7 @@ for more information about using a special vllm-openai docker image for inferenc
 Optionally, vLLM can be installed from nightly:

 ```bash
-pip install --no-build-isolation --pre -U vllm --extra-index-url https://wheels.vllm.ai/nightly
+uv pip install --no-build-isolation --pre -U vllm --extra-index-url https://wheels.vllm.ai/nightly
 ```
 and the vLLM server can be started with the following command (modify `--tensor-parallel-size 8` to match your environment):
 ```bash
--- a/examples/gpt-oss/gpt-oss-120b-fft-fsdp2-offload.yaml
+++ b/examples/gpt-oss/gpt-oss-120b-fft-fsdp2-offload.yaml
@@ -32,10 +32,6 @@ wandb_watch:
 wandb_name:
 wandb_log_model:

-trackio_project_name:
-trackio_run_name:
-trackio_space_id:
-
 gradient_accumulation_steps: 2
 micro_batch_size: 1
 num_epochs: 1
--- a/examples/gpt-oss/gpt-oss-20b-fft-deepspeed-zero3.yaml
+++ b/examples/gpt-oss/gpt-oss-20b-fft-deepspeed-zero3.yaml
@@ -28,10 +28,6 @@ wandb_watch:
 wandb_name:
 wandb_log_model:

-trackio_project_name:
-trackio_run_name:
-trackio_space_id:
-
 gradient_accumulation_steps: 2
 micro_batch_size: 1
 num_epochs: 1
--- a/examples/gpt-oss/gpt-oss-20b-fft-fsdp2-offload.yaml
+++ b/examples/gpt-oss/gpt-oss-20b-fft-fsdp2-offload.yaml
@@ -29,10 +29,6 @@ wandb_watch:
 wandb_name:
 wandb_log_model:

-trackio_project_name:
-trackio_run_name:
-trackio_space_id:
-
 gradient_accumulation_steps: 2
 micro_batch_size: 1
 num_epochs: 1
--- a/examples/gpt-oss/gpt-oss-20b-fft-fsdp2.yaml
+++ b/examples/gpt-oss/gpt-oss-20b-fft-fsdp2.yaml
@@ -28,10 +28,6 @@ wandb_watch:
 wandb_name:
 wandb_log_model:

-trackio_project_name:
-trackio_run_name:
-trackio_space_id:
-
 gradient_accumulation_steps: 2
 micro_batch_size: 1
 num_epochs: 1
--- a/examples/gpt-oss/gpt-oss-20b-sft-lora-singlegpu.yaml
+++ b/examples/gpt-oss/gpt-oss-20b-sft-lora-singlegpu.yaml
@@ -41,10 +41,6 @@ wandb_watch:
 wandb_name:
 wandb_log_model:

-trackio_project_name:
-trackio_run_name:
-trackio_space_id:
-
 gradient_accumulation_steps: 8
 micro_batch_size: 1
 num_epochs: 1
--- a/examples/gpt-oss/gpt-oss-safeguard-20b-sft-lora-singlegpu.yaml
+++ b/examples/gpt-oss/gpt-oss-safeguard-20b-sft-lora-singlegpu.yaml
@@ -1,71 +0,0 @@
-base_model: openai/gpt-oss-safeguard-20b
-use_kernels: true
-model_quantization_config: Mxfp4Config
-model_quantization_config_kwargs:
-  dequantize: true
-
-plugins:
-  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
-
-experimental_skip_move_to_device: true  # prevent OOM by not putting model to GPU before sharding
-
-datasets:
-  - path: HuggingFaceH4/Multilingual-Thinking
-    type: chat_template
-    field_thinking: thinking
-    template_thinking_key: thinking
-
-dataset_prepared_path: last_run_prepared
-val_set_size: 0
-output_dir: ./outputs/gpt-oss-safeguard-out/
-
-sequence_len: 4096
-sample_packing: true
-
-adapter: lora
-lora_r: 8
-lora_alpha: 16
-lora_dropout: 0.0  # dropout not supported when using LoRA over expert parameters
-lora_target_linear: true
-
-# TODO: not supported for now, see peft#2710
-#lora_target_parameters:  # target the experts in the last two layers
-#  - "22._checkpoint_wrapped_module.mlp.experts.gate_up_proj"
-#  - "22._checkpoint_wrapped_module.mlp.experts.down_proj"
-#  - "23._checkpoint_wrapped_module.mlp.experts.gate_up_proj"
-#  - "23._checkpoint_wrapped_module.mlp.experts.down_proj"
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-trackio_project_name:
-trackio_run_name:
-trackio_space_id:
-
-gradient_accumulation_steps: 8
-micro_batch_size: 1
-num_epochs: 1
-
-optimizer: adamw_torch_8bit
-lr_scheduler: constant_with_warmup
-learning_rate: 2e-4
-
-bf16: true
-tf32: true
-
-flash_attention: true
-attn_implementation: kernels-community/vllm-flash-attn3  # this is not needed if using flash_attn >= 2.8.3
-
-gradient_checkpointing: true
-activation_offloading: true
-
-logging_steps: 1
-saves_per_epoch: 1
-warmup_ratio: 0.1
-
-special_tokens:
-eot_tokens:
-  - "<|end|>"
--- a/examples/granite4/README.md
+++ b/examples/granite4/README.md
@@ -1,65 +0,0 @@
-# Finetune IBM's Granite 4.0 with Axolotl
-
-[Granite 4.0](https://huggingface.co/collections/ibm-granite/granite-40-language-models) are a family of open source models trained by IBM Research.
-
-This guide shows how to fine-tune it with Axolotl with multi-turn conversations and proper masking.
-
-## Getting started
-
-1. Install Axolotl following the [installation guide](https://docs.axolotl.ai/docs/installation.html). You need to install from main as Granite4 is only on nightly or use our latest [Docker images](https://docs.axolotl.ai/docs/docker.html).
-
-    Here is an example of how to install from main for pip:
-
-```bash
-# Ensure you have Pytorch installed (Pytorch 2.7.1 min)
-git clone https://github.com/axolotl-ai-cloud/axolotl.git
-cd axolotl
-
-pip3 install packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation -e '.[flash-attn]'
-
-# Install CCE https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy
-python scripts/cutcrossentropy_install.py | sh
-```
-
-2. Run the finetuning example:
-
-```bash
-axolotl train examples/granite4/granite-4.0-tiny-fft.yaml
-```
-
-This config uses about 40.8GiB VRAM.
-
-Let us know how it goes. Happy finetuning! 🚀
-
-### TIPS
-
- Read more on how to load your own dataset at [docs](https://docs.axolotl.ai/docs/dataset_loading.html).
- The dataset format follows the OpenAI Messages format as seen [here](https://docs.axolotl.ai/docs/dataset-formats/conversation.html#chat_template).
-
-### Limitation
-
-Adapter finetuning does not work at the moment. It would error with
-
-```bash
-RuntimeError: mat1 and mat2 shapes cannot be multiplied (4096x3072 and 1x1179648)
-```
-
-In addition, if adapter training works, `lora_target_linear: true` will not work due to:
-```bash
-ValueError: Target module GraniteMoeHybridParallelExperts() is not supported.
-```
-
-## Optimization Guides
-
- [Multi-GPU Training](https://docs.axolotl.ai/docs/multi-gpu.html)
- [Multi-Node Training](https://docs.axolotl.ai/docs/multi-node.html)
- [LoRA Optimizations](https://docs.axolotl.ai/docs/lora_optims.html)
-
-## Related Resources
-
- [Granite Docs](https://www.ibm.com/granite/docs/models/granite)
- [Axolotl Docs](https://docs.axolotl.ai)
- [Axolotl Website](https://axolotl.ai)
- [Axolotl GitHub](https://github.com/axolotl-ai-cloud/axolotl)
- [Axolotl Discord](https://discord.gg/7m9sfhzaf3)
--- a/examples/granite4/granite-4.0-tiny-fft.yaml
+++ b/examples/granite4/granite-4.0-tiny-fft.yaml
@@ -1,45 +0,0 @@
-base_model: ibm-granite/granite-4.0-tiny-preview
-
-# Automatically upload checkpoint and final model to HF
-# hub_model_id: username/custom_model_name
-
-plugins:
-  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
-
-datasets:
-  - path: fozziethebeat/alpaca_messages_2k_test
-    type: chat_template
-
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.1
-output_dir: ./outputs/model-out
-
-sequence_len: 2048
-sample_packing: true
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 1
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-bf16: auto
-tf32: false
-
-gradient_checkpointing: true
-resume_from_checkpoint:
-logging_steps: 1
-flash_attention: true
-
-warmup_ratio: 0.1
-evals_per_epoch: 1
-saves_per_epoch: 1
-
-# save_first_step: true  # uncomment this to validate checkpoint saving works with your config
--- a/examples/hunyuan/README.md
+++ b/examples/hunyuan/README.md
@@ -13,8 +13,8 @@ Tencent released a family of opensource models called HunYuan with varying param
 git clone https://github.com/axolotl-ai-cloud/axolotl.git
 cd axolotl

-pip3 install packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation -e '.[flash-attn]'
+uv sync
+uv pip install flash-attn --no-build-isolation

 # Install CCE https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy
 python scripts/cutcrossentropy_install.py | sh
--- a/examples/internvl3_5/README.md
+++ b/examples/internvl3_5/README.md
@@ -1,43 +0,0 @@
-# Finetune OpenGV's InternVL with Axolotl
-
-[InternVL 3.5](https://huggingface.co/OpenGVLab/InternVL3_5-8B-HF) is a family of powerful vision-language models supporting dynamic resolution and multi-image understanding by OpenGV. It features a ViT-style vision encoder and strong language model backbone for tasks like visual question answering, OCR, and scene text understanding.
-
-This guide shows how to fine-tune it with Axolotl.
-
-## Getting started
-
-1. Install Axolotl following the [installation guide](https://docs.axolotl.ai/docs/installation.html).
-
-2. Install `timm` for vision model support:
-
-    ```bash
-    pip install timm==1.0.19
-    ```
-
-3. Install [Cut Cross Entropy](https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy) to reduce training VRAM usage.
-
-4. Run the finetuning example:
-
-    ```bash
-    axolotl train examples/internvl3_5/internvl3_5-8b-qlora.yml
-    ```
-
-This config uses about 8.21 GiB VRAM. Let us know how it goes. Happy finetuning! 🚀
-
-### Tips
-
- You can run a full finetuning by removing the `adapter: qlora` and `load_in_4bit: true` from the config.
- Read more on how to load your own dataset at [docs](https://docs.axolotl.ai/docs/dataset_loading.html).
- The dataset format follows the multi-modal format as seen [here](https://docs.axolotl.ai/docs/multimodal.html#dataset-format).
-
-## Optimization Guides
-
-Please check the [Optimizations doc](https://docs.axolotl.ai/docs/optimizations.html).
-
-## Related Resources
-
- [InternVL Paper](https://huggingface.co/papers/2508.18265)
- [Axolotl Docs](https://docs.axolotl.ai)
- [Axolotl Website](https://axolotl.ai)
- [Axolotl GitHub](https://github.com/axolotl-ai-cloud/axolotl)
- [Axolotl Discord](https://discord.gg/7m9sfhzaf3)
--- a/examples/internvl3_5/internvl3_5-8b-qlora.yml
+++ b/examples/internvl3_5/internvl3_5-8b-qlora.yml
@@ -1,61 +0,0 @@
-base_model: OpenGVLab/InternVL3_5-8B-HF
-processor_type: AutoProcessor
-
-plugins:
-  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
-
-load_in_4bit: true
-
-# these 3 lines are needed for now to handle vision chat templates w images
-skip_prepare_dataset: true
-remove_unused_columns: false
-sample_packing: false
-
-datasets:
-  - path: HuggingFaceH4/llava-instruct-mix-vsft
-    type: chat_template
-    split: train[:1%]
-    field_messages: messages
-
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-output_dir: ./outputs/out
-
-adapter: qlora
-lora_model_dir:
-
-sequence_len: 2048
-
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules: 'model.language_model.layers.[\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj'
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 1
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-bf16: true
-fp16:
-tf32: true
-
-gradient_checkpointing: true
-logging_steps: 1
-flash_attention: true
-eager_attention:
-
-warmup_ratio: 0.1
-evals_per_epoch: 1
-saves_per_epoch: 1
-weight_decay: 0.0
-
-# save_first_step: true  # uncomment this to validate checkpoint saving works with your config
--- a/examples/jamba/qlora_fsdp_large.yaml
+++ b/examples/jamba/qlora_fsdp_large.yaml
@@ -19,6 +19,7 @@ datasets:
 dataset_prepared_path: last_run_prepared
 val_set_size: 0.0
 output_dir: jamba-large-fsdp-qlora-ft
+save_safetensors: true
 adapter: qlora
 sequence_len: 2048
 sample_packing: true
--- a/examples/kimi-linear/README.md
+++ b/examples/kimi-linear/README.md
@@ -1,47 +0,0 @@
-# Finetune MoonshotAI's Kimi Linear with Axolotl
-
-[Kimi Linear](https://huggingface.co/collections/moonshotai/kimi-linear-a3b) is a MoE model (48B total, 3B active) by MoonshotAI using a hybrid linear attention architecture to achieve a 1M token context length. It uses Kimi Delta Attention (KDA), a refined version of Gated DeltaNet that reduces KV cache size by up to 75% and boosts decoding throughput by up to 6x for long contexts.
-
-This guide shows how to fine-tune it with Axolotl with multi-turn conversations and proper masking.
-
-**Note:** Axolotl uses experimental training code for Kimi Linear as their original modeling code is inference-only.
-
-## Getting started
-
-1. Install Axolotl following the [installation guide](https://docs.axolotl.ai/docs/installation.html).
-
-2. Install CCE via [docs](https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy)
-
-3. Run the finetuning example:
-
-    ```bash
-    axolotl train examples/kimi-linear/kimi-48b-lora.yaml
-    ```
-
-This config uses about 98.7GiB VRAM.
-
-Let us know how it goes. Happy finetuning!
-
-### TIPS
-
- Kimi Linear requires `trust_remote_code: true`.
- You can run a full finetuning by removing the `adapter: lora` and `load_in_8bit: true`.
- Read more on how to load your own dataset at [docs](https://docs.axolotl.ai/docs/dataset_loading.html)
- The dataset format follows the OpenAI Messages format as seen [here](https://docs.axolotl.ai/docs/dataset-formats/conversation.html#chat_template)
-
-## Optimization Guides
-
-See 👉 [docs](https://docs.axolotl.ai/docs/optimizations.html).
-
-## Limitations
-
-This is not yet compatible with MoE kernels from transformers v5.
-
-## Related Resources
-
- [Kimi Linear Paper](https://huggingface.co/papers/2510.26692)
- [Kimi Linear GitHub](https://github.com/MoonshotAI/Kimi-Linear)
- [Axolotl Docs](https://docs.axolotl.ai)
- [Axolotl Website](https://axolotl.ai)
- [Axolotl GitHub](https://github.com/axolotl-ai-cloud/axolotl)
- [Axolotl Discord](https://discord.gg/7m9sfhzaf3)
--- a/examples/kimi-linear/kimi-48b-lora.yaml
+++ b/examples/kimi-linear/kimi-48b-lora.yaml
@@ -1,81 +0,0 @@
-base_model: moonshotai/Kimi-Linear-48B-A3B-Instruct
-
-# Automatically upload checkpoint and final model to HF
-# hub_model_id: username/custom_model_name
-
-trust_remote_code: true
-
-plugins:
-  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
-
-load_in_8bit: true
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: fozziethebeat/alpaca_messages_2k_test
-    type: chat_template
-    split: train
-
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.2
-output_dir: ./outputs/lora-out
-
-adapter: lora
-lora_model_dir:
-
-sequence_len: 2048
-sample_packing: true
-pad_to_sequence_len: true
-
-lora_r: 16
-lora_alpha: 32
-lora_dropout: 0.05
-lora_fan_in_fan_out:
-lora_target_modules:
-  - gate_proj
-  - down_proj
-  - up_proj
-  - q_proj
-  - v_proj
-  - k_proj
-  - o_proj
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 2
-micro_batch_size: 2
-num_epochs: 1
-optimizer: adamw_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: auto
-fp16:
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-flash_attention: true
-
-loss_watchdog_threshold: 5.0
-loss_watchdog_patience: 3
-
-warmup_ratio: 0.1
-evals_per_epoch: 2
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
--- a/examples/llama-3/3b-fp8-fsdp2.yaml
+++ b/examples/llama-3/3b-fp8-fsdp2.yaml
@@ -29,6 +29,7 @@ flex_attention: true
 flex_attn_compile_kwargs:
  dynamic: false
  mode: max-autotune-no-cudagraphs
+
 torch_compile: true

 wandb_project:
--- a/examples/llama-3/opentelemetry-qlora.yml
+++ b/examples/llama-3/opentelemetry-qlora.yml
@@ -1,50 +0,0 @@
-base_model: NousResearch/Llama-3.2-1B
-model_type: AutoModelForCausalLM
-tokenizer_type: AutoTokenizer
-
-load_in_4bit: true
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-
-output_dir: ./outputs/opentelemetry-example
-
-adapter: qlora
-sequence_len: 512
-sample_packing: false
-
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-
-# OpenTelemetry Configuration
-use_otel_metrics: true
-otel_metrics_host: "localhost"
-otel_metrics_port: 8000
-
-# Disable WandB
-use_wandb: false
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 1
-optimizer: paged_adamw_32bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-bf16: auto
-tf32: false
-
-gradient_checkpointing: true
-logging_steps: 1
-flash_attention: false
-
-warmup_ratio: 0.1
-evals_per_epoch: 2
-saves_per_epoch: 1
-weight_decay: 0.0
-
-special_tokens:
-  pad_token: "<|end_of_text|>"
--- a/examples/llama-3/qlora-1b-gdpo.yaml
+++ b/examples/llama-3/qlora-1b-gdpo.yaml
@@ -1,68 +0,0 @@
-base_model: meta-llama/Llama-3.2-1B-Instruct
-
-chat_template: llama3
-
-rl: gdpo
-
-trl:
-  beta: 0.001
-  max_completion_length: 128
-  num_generations: 2
-  temperature: 0.7
-  top_p: 0.95
-
-  use_vllm: false
-
-
-  multi_objective_aggregation: normalize_then_sum
-
-  reward_funcs:
-    - rwd.format_reward
-    - rwd.correctness_reward
-  reward_weights: [1.0, 2.0]
-
-  log_completions: true
-  num_completions_to_print: 3
-  scale_rewards: true
-
-datasets:
-  - path: openai/gsm8k
-    name: main
-    split: train[:1000]
-    type: rwd.gsm8k_transform
-
-val_set_size: 0.0
-output_dir: ./outputs/llama3-gdpo-out
-
-sequence_len: 512
-sample_packing: false
-pad_to_sequence_len: false
-
-gradient_accumulation_steps: 8
-micro_batch_size: 1
-num_epochs: 1
-max_steps: 100
-
-optimizer: adamw_torch_fused
-lr_scheduler: cosine
-learning_rate: 5e-5
-weight_decay: 0.01
-warmup_steps: 10
-
-bf16: auto
-tf32: true
-
-gradient_checkpointing: true
-gradient_checkpointing_kwargs:
-  use_reentrant: false
-
-flash_attention: true
-logging_steps: 1
-save_steps: 50
-save_safetensors: true
-
-special_tokens:
-  pad_token: "<|end_of_text|>"
-
-
-seed: 42
--- a/examples/llama-3/qlora-fsdp-405b.yaml
+++ b/examples/llama-3/qlora-fsdp-405b.yaml
@@ -12,6 +12,7 @@ datasets:
 dataset_prepared_path: last_run_prepared
 val_set_size: 0.0
 output_dir: ./outputs/out/qlora-llama3_1-405b
+save_safetensors: true

 adapter: qlora

--- a/examples/magistral/README.md
+++ b/examples/magistral/README.md
@@ -13,9 +13,14 @@ Thanks to the team at MistralAI for giving us early access to prepare for these
    Here is an example of how to install from pip:

 ```bash
-# Ensure you have Pytorch installed (Pytorch 2.7.0 min)
-pip3 install packaging==26.0 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
+# Ensure you have PyTorch installed (PyTorch 2.6.0 min)
+# Option A: manage dependencies in your project
+uv add 'axolotl>=0.12.0'
+uv pip install flash-attn --no-build-isolation
+
+# Option B: quick install
+uv pip install 'axolotl>=0.12.0'
+uv pip install flash-attn --no-build-isolation
 ```

 2. Install [Cut Cross Entropy](https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy) to reduce training VRAM usage
--- a/examples/magistral/think/README.md
+++ b/examples/magistral/think/README.md
@@ -5,7 +5,6 @@ This guide covers fine-tuning [Magistral Small 2507](https://huggingface.co/mist
 ## Prerequisites

 Before starting, ensure you have:
-
 - Installed Axolotl (see [main README](../README.md))

 ## Getting Started
@@ -13,7 +12,7 @@ Before starting, ensure you have:
 Run the thinking model fine-tuning:

 ```bash
-axolotl train examples/magistral/think/magistral-small-think-qlora.yaml
+axolotl train magistral-small-think-qlora.yaml
 ```

 This config uses about 19.1 GiB VRAM.
--- a/examples/magistral/vision/README.md
+++ b/examples/magistral/vision/README.md
@@ -5,8 +5,7 @@ This guide covers fine-tuning [Magistral Small 2509](https://huggingface.co/mist
 ## Prerequisites

 Before starting, ensure you have:
-
- Installed Axolotl from source (see [main README](../README.md))
+- Installed Axolotl from source (see [main README](../README.md#getting-started))

 ## Getting started

@@ -22,7 +21,7 @@ Before starting, ensure you have:

 3. Run the fine-tuning:
   ```bash
-   axolotl train examples/magistral/vision/magistral-small-vision-24B-qlora.yml
+   axolotl train magistral-small-vision-24B-qlora.yml
   ```

 This config uses about 17GiB VRAM.
--- a/examples/mamba/config.yml
+++ b/examples/mamba/config.yml
@@ -47,5 +47,6 @@ saves_per_epoch: 1
 weight_decay: 0.0
 special_tokens:
 tokens:
+save_safetensors: False

 # save_first_step: true  # uncomment this to validate checkpoint saving works with your config
--- a/examples/mimo/README.md
+++ b/examples/mimo/README.md
@@ -1,39 +0,0 @@
-# Finetune Xiaomi's MiMo with Axolotl
-
-[MiMo](https://huggingface.co/XiaomiMiMo/MiMo-7B-RL) is a family of models trained from scratch for reasoning tasks, incorporating **Multiple-Token Prediction (MTP)** as an additional training objective for enhanced performance and faster inference. Pre-trained on ~25T tokens with a three-stage data mixture strategy and optimized reasoning pattern density.
-
-This guide shows how to fine-tune it with Axolotl with multi-turn conversations and proper masking.
-
-## Getting started
-
-1. Install Axolotl following the [installation guide](https://docs.axolotl.ai/docs/installation.html).
-
-2. Run the finetuning example:
-
-    ```bash
-    axolotl train examples/mimo/mimo-7b-qlora.yaml
-    ```
-
-This config uses about 17.2 GiB VRAM. Let us know how it goes. Happy finetuning! 🚀
-
-### Tips
-
- You can run a full finetuning by removing the `adapter: qlora` and `load_in_4bit: true` from the config.
- Read more on how to load your own dataset at [docs](https://docs.axolotl.ai/docs/dataset_loading.html).
- The dataset format follows the OpenAI Messages format as seen [here](https://docs.axolotl.ai/docs/dataset-formats/conversation.html#chat_template).
-
-## Optimization Guides
-
-Please check the [Optimizations doc](https://docs.axolotl.ai/docs/optimizations.html).
-
-## Limitations
-
-**Cut Cross Entropy (CCE)**: Currently not supported. We plan to include CCE support for MiMo in the near future.
-
-## Related Resources
-
- [MiMo Paper](https://arxiv.org/abs/2505.07608)
- [Axolotl Docs](https://docs.axolotl.ai)
- [Axolotl Website](https://axolotl.ai)
- [Axolotl GitHub](https://github.com/axolotl-ai-cloud/axolotl)
- [Axolotl Discord](https://discord.gg/7m9sfhzaf3)
--- a/examples/mimo/mimo-7b-qlora.yaml
+++ b/examples/mimo/mimo-7b-qlora.yaml
@@ -1,67 +0,0 @@
-base_model: XiaomiMiMo/MiMo-7B-RL
-trust_remote_code: true
-revision_of_model: 6299b5a
-
-# Automatically upload checkpoint and final model to HF
-# hub_model_id: username/custom_model_name
-
-# CCE - N/A as of now
-# plugins:
-#   - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
-
-load_in_8bit: false
-load_in_4bit: true
-
-datasets:
-  - path: fozziethebeat/alpaca_messages_2k_test
-    type: chat_template
-
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.1
-output_dir: ./outputs/lora-out
-
-adapter: qlora
-lora_model_dir:
-
-sequence_len: 2048
-sample_packing: true
-
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-lora_target_modules:
-  - gate_proj
-  - down_proj
-  - up_proj
-  - q_proj
-  - v_proj
-  - k_proj
-  - o_proj
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 1
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-bf16: auto
-tf32: false
-
-gradient_checkpointing: true
-resume_from_checkpoint:
-logging_steps: 1
-flash_attention: true
-
-warmup_ratio: 0.1
-evals_per_epoch: 1
-saves_per_epoch: 1
-
-# save_first_step: true  # uncomment this to validate checkpoint saving works with your config
--- a/examples/ministral/README.md
+++ b/examples/ministral/README.md
@@ -1,50 +0,0 @@
-# Finetune Ministral with Axolotl
-
-Ministral is a family of openweight models from MistralAI found on [HuggingFace](mistralai/Ministral-8B-Instruct-2410). This guide shows how to fine-tune it with Axolotl with multi-turn conversations and proper masking.
-
-## Getting started
-
-1. Install Axolotl following the [installation guide](https://docs.axolotl.ai/docs/installation.html).
-
-2. Install [Cut Cross Entropy](https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy) to reduce training VRAM usage.
-
-3. Run the finetuning example:
-
-    ```bash
-    axolotl train examples/ministral/ministral-small-qlora.yaml
-    ```
-
-This config uses about 8.76 GiB VRAM.
-
-Let us know how it goes. Happy finetuning! 🚀
-
-### Tips
-
- We recommend adding the same/similar SystemPrompt that the model is tuned for. You can find this within the repo's files titled `SYSTEM_PROMPT.txt`.
- You can run a full finetuning by removing the `adapter: qlora` and `load_in_4bit: true` from the config.
- Read more on how to load your own dataset at [docs](https://docs.axolotl.ai/docs/dataset_loading.html).
- The text dataset format follows the OpenAI Messages format as seen [here](https://docs.axolotl.ai/docs/dataset-formats/conversation.html#chat_template).
-
-## Optimization Guides
-
-Please check the [Optimizations doc](https://docs.axolotl.ai/docs/optimizations.html).
-
-## Limitations
-
-We only support the `mistral-common` tokenizer for Supervised Fine-tuning at the moment and for `type: chat_template` only.
-
-In addition, we do not support overriding tokens yet.
-
-## Related Resources
-
- [MistralAI Ministral Blog](https://mistral.ai/news/ministraux)
- [Axolotl Docs](https://docs.axolotl.ai)
- [Axolotl Website](https://axolotl.ai)
- [Axolotl GitHub](https://github.com/axolotl-ai-cloud/axolotl)
- [Axolotl Discord](https://discord.gg/7m9sfhzaf3)
-
-
-## Future Work
-
- Add parity to Preference Tuning, RL, etc.
- Add parity to other tokenizer configs like overriding tokens.
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Dan Saunders	ffb307a8a7	update tags	2025-10-04 12:10:43 -04:00
Dan Saunders	915c258c6e	contrib fix	2025-10-04 11:53:48 -04:00
Dan Saunders	1e58235c38	contrib	2025-10-04 11:47:56 -04:00
Dan Saunders	5753c5b89c	mypy 3.11	2025-10-04 11:26:10 -04:00
Dan Saunders	18d78f02cf	fix sdist	2025-10-04 09:48:19 -04:00
Dan Saunders	923181aaed	Merge branch 'main' into uv-first	2025-10-04 09:07:22 -04:00
Dan Saunders	786f1a3ff9	add missing dep	2025-10-03 12:46:15 -04:00
Dan Saunders	26418e6f9a	Fix	2025-10-02 12:53:51 -04:00
Dan Saunders	19fe84ef46	Fix	2025-10-02 12:33:13 -04:00
Dan Saunders	98730868e7	fix	2025-10-02 12:07:58 -04:00
Dan Saunders	5771a65b88	fix	2025-10-02 11:20:23 -04:00
Dan Saunders	f912d1bb97	fix	2025-10-02 10:57:09 -04:00
Dan Saunders	0250e5f87c	fix	2025-10-01 17:02:31 -04:00
Dan Saunders	274c579d81	handle race cond	2025-10-01 16:31:39 -04:00
Dan Saunders	ccd2f12335	fix?	2025-10-01 16:18:40 -04:00
Dan Saunders	00e0238501	fix?	2025-10-01 16:15:06 -04:00
Dan Saunders	f782957002	fix	2025-10-01 14:44:14 -04:00
Dan Saunders	f2f66f2bb9	fix	2025-10-01 13:16:35 -04:00
Dan Saunders	013474eb70	mirror dev deps	2025-10-01 12:58:20 -04:00
Dan Saunders	6dc9816722	fix	2025-10-01 10:18:50 -04:00
Dan Saunders	74715125b6	fix	2025-09-30 17:28:15 -04:00
Dan Saunders	f0f3bfbdf0	fix	2025-09-30 17:25:07 -04:00
Dan Saunders	022ef7ab4e	fix	2025-09-30 17:12:23 -04:00
Dan Saunders	04533b79d4	fix	2025-09-30 17:07:57 -04:00
Dan Saunders	19de29be19	fix	2025-09-30 17:00:25 -04:00
Dan Saunders	ec75aa5889	fix	2025-09-30 16:52:37 -04:00
Dan Saunders	cf4e3fac64	version fix	2025-09-30 16:48:55 -04:00
Dan Saunders	69df309cbb	separate out flash-attn install (sadly)	2025-09-30 14:58:56 -04:00
Dan Saunders	b436ecf61f	fix	2025-09-29 12:08:23 -04:00
Dan Saunders	f137ce50ec	grpclib	2025-09-28 21:28:53 -04:00
Dan Saunders	4131bcf769	fix?	2025-09-28 20:04:44 -04:00
Dan Saunders	64fea39978	add back protobuf	2025-09-28 19:18:06 -04:00
Dan Saunders	4966496b98	revert	2025-09-27 15:16:17 -04:00
Dan Saunders	66a9e4fced	fix?	2025-09-26 23:08:29 -04:00
Dan Saunders	15d35b76bb	fixes	2025-09-26 21:50:35 -04:00
Dan Saunders	0d53e0fe8f	fix -E -> --extra	2025-09-26 21:21:10 -04:00
Dan Saunders	9344fa5e8c	fix install scripts (?)	2025-09-26 20:35:08 -04:00
Dan Saunders	c702edae5f	use container venv	2025-09-26 20:19:14 -04:00
Dan Saunders	dfaf76659f	pip install --system flag	2025-09-26 19:53:51 -04:00
Dan Saunders	26a58bb8af	git SHA	2025-09-26 19:39:08 -04:00
Dan Saunders	cec2490903	prune 2.7.0, docker cache invalidation	2025-09-26 19:11:28 -04:00
Dan Saunders	dfa5224908	uv.lock	2025-09-26 20:47:01 +00:00
Dan Saunders	ddafc6ef80	referring to temp docker images	2025-09-26 16:04:39 -04:00
Dan Saunders	ad56e600e3	remove 2.7.0 images	2025-09-26 14:40:41 -04:00
Dan Saunders	18d9456297	loosen xformers range	2025-09-26 13:32:11 -04:00
Dan Saunders	da5ede6372	lockfile	2025-09-26 17:27:31 +00:00
Dan Saunders	6cbca1ffb2	loosen xformers range	2025-09-26 13:26:13 -04:00
Dan Saunders	2e082d47cc	constrain torch version	2025-09-26 13:20:45 -04:00
Dan Saunders	b4c6675cd2	fix	2025-09-26 13:13:13 -04:00
Dan Saunders	828131332a	no -y flag for uv pip install	2025-09-26 13:04:33 -04:00
Dan Saunders	273a03f85c	simplify install script	2025-09-26 12:55:55 -04:00
Dan Saunders	9bbe2cfe0f	handle vllm pinned conflict	2025-09-26 12:27:11 -04:00
Dan Saunders	64da8f0044	depr warning	2025-09-26 11:59:58 -04:00
Dan Saunders	1fa0a98e38	update lock	2025-09-26 15:44:46 +00:00
Dan Saunders	8d542d9d63	deps up to date	2025-09-26 10:39:34 -04:00
Dan Saunders	a4565476e0	find-links for wheels, auto-gptq -> gptqmodel	2025-09-26 10:26:44 -04:00
Dan Saunders	02dc263338	updates	2025-09-26 10:26:44 -04:00
Dan Saunders	2acd3e1242	dep	2025-09-26 10:26:44 -04:00
Dan Saunders	0437c1a4ba	auto-gptq -> gptqmodel	2025-09-26 10:26:44 -04:00
Dan Saunders	ef150fd973	updates	2025-09-26 10:26:44 -04:00
Dan Saunders	47ad92c6b9	fix	2025-09-26 10:26:44 -04:00
Dan Saunders	f0fee9c56c	req	2025-09-26 10:26:44 -04:00
Dan Saunders	37d07bd7f7	coderabbito, improvements	2025-09-26 10:26:44 -04:00
Dan Saunders	4c81172917	coderabbito	2025-09-26 10:26:21 -04:00
Dan Saunders	cd8c769e84	Update cicd/Dockerfile.jinja Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>	2025-09-26 10:26:21 -04:00
Dan Saunders	0d60046d08	Update .github/workflows/pypi.yml Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>	2025-09-26 10:26:21 -04:00
Dan Saunders	c110e3eb48	remove setup.py, requirements.txt and refs	2025-09-26 10:26:21 -04:00
Dan Saunders	95c259b3fb	depr warning	2025-09-26 10:26:21 -04:00
Dan Saunders	d1fd505813	update	2025-09-26 10:26:21 -04:00
Dan Saunders	1334281d50	docker fix	2025-09-26 10:26:21 -04:00
Dan Saunders	98f230d864	cleanup	2025-09-26 10:26:21 -04:00
Dan Saunders	02f308351c	fix	2025-09-26 10:25:58 -04:00
Dan Saunders	3b91e8174d	fix	2025-09-26 10:25:58 -04:00
Dan Saunders	40d906fb33	lint	2025-09-26 10:25:58 -04:00
Dan Saunders	89d5323c13	fix	2025-09-26 10:25:58 -04:00
Dan Saunders	df870f6a8f	fix	2025-09-26 10:24:59 -04:00
Dan Saunders	f500aaa490	fix	2025-09-26 10:24:59 -04:00
Dan Saunders	9ec33f52e3	wip	2025-09-26 10:24:59 -04:00
Dan Saunders	b453562c01	fixes	2025-09-26 10:24:59 -04:00
Dan Saunders	367f7eb3a6	fix	2025-09-26 10:24:59 -04:00
Dan Saunders	e888e38ce7	fix	2025-09-26 10:24:59 -04:00
Dan Saunders	400120af2d	wip	2025-09-26 10:24:59 -04:00
Dan Saunders	459e5f9b16	lint	2025-09-26 10:24:59 -04:00
Dan Saunders	43f6f84269	wip	2025-09-26 10:24:59 -04:00
Dan Saunders	36c4ab11f9	wip	2025-09-26 10:24:59 -04:00
Dan Saunders	2f4e4ef604	wip	2025-09-26 10:24:59 -04:00
Dan Saunders	aee03fc636	wip	2025-09-26 10:24:59 -04:00
Dan Saunders	255b818fbc	rebase	2025-09-26 10:24:59 -04:00
Dan Saunders	332ee74f32	rebase	2025-09-26 10:24:07 -04:00
Dan Saunders	3b0d2ac5c0	rebase	2025-09-26 10:21:49 -04:00
Dan Saunders	9462a1bf79	wip	2025-09-26 10:21:49 -04:00
Dan Saunders	8e9386c799	go uv first	2025-09-26 09:57:09 -04:00