smart resize embeddings

2023-08-14 23:44:15 -04:00
192 changed files with 4185 additions and 17556 deletions
--- a/.github/CODE_OF_CONDUCT.md
+++ b/.github/CODE_OF_CONDUCT.md
@@ -1,129 +0,0 @@
-# Contributor Covenant Code of Conduct
-
-## Our Pledge
-
-We as members, contributors, and leaders pledge to make participation in our
-community a harassment-free experience for everyone, regardless of age, body
-size, visible or invisible disability, ethnicity, sex characteristics, gender
-identity and expression, level of experience, education, socio-economic status,
-nationality, personal appearance, race, religion, or sexual identity
-and orientation.
-
-We pledge to act and interact in ways that contribute to an open, welcoming,
-diverse, inclusive, and healthy community.
-
-## Our Standards
-
-Examples of behavior that contributes to a positive environment for our
-community include:
-
-* Demonstrating empathy and kindness toward other people
-* Being respectful of differing opinions, viewpoints, and experiences
-* Giving and gracefully accepting constructive feedback
-* Accepting responsibility and apologizing to those affected by our mistakes,
-  and learning from the experience
-* Focusing on what is best not just for us as individuals, but for the
-  overall community
-
-Examples of unacceptable behavior include:
-
-* The use of sexualized language or imagery, and sexual attention or
-  advances of any kind
-* Trolling, insulting or derogatory comments, and personal or political attacks
-* Public or private harassment
-* Publishing others' private information, such as a physical or email
-  address, without their explicit permission
-* Other conduct which could reasonably be considered inappropriate in a
-  professional setting
-
-## Enforcement Responsibilities
-
-Community leaders are responsible for clarifying and enforcing our standards of
-acceptable behavior and will take appropriate and fair corrective action in
-response to any behavior that they deem inappropriate, threatening, offensive,
-or harmful.
-
-Community leaders have the right and responsibility to remove, edit, or reject
-comments, commits, code, wiki edits, issues, and other contributions that are
-not aligned to this Code of Conduct, and will communicate reasons for moderation
-decisions when appropriate.
-
-## Scope
-
-This Code of Conduct applies within all community spaces, and also applies when
-an individual is officially representing the community in public spaces.
-Examples of representing our community include using an official e-mail address,
-posting via an official social media account, or acting as an appointed
-representative at an online or offline event.
-
-## Enforcement
-
-Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported to the community leaders responsible for enforcement on Discord
-at https://discord.gg/QYF8QrtEUm
-
-All complaints will be reviewed and investigated promptly and fairly.
-
-All community leaders are obligated to respect the privacy and security of the
-reporter of any incident.
-
-## Enforcement Guidelines
-
-Community leaders will follow these Community Impact Guidelines in determining
-the consequences for any action they deem in violation of this Code of Conduct:
-
-### 1. Correction
-
-**Community Impact**: Use of inappropriate language or other behavior deemed
-unprofessional or unwelcome in the community.
-
-**Consequence**: A private, written warning from community leaders, providing
-clarity around the nature of the violation and an explanation of why the
-behavior was inappropriate. A public apology may be requested.
-
-### 2. Warning
-
-**Community Impact**: A violation through a single incident or series
-of actions.
-
-**Consequence**: A warning with consequences for continued behavior. No
-interaction with the people involved, including unsolicited interaction with
-those enforcing the Code of Conduct, for a specified period of time. This
-includes avoiding interactions in community spaces as well as external channels
-like social media. Violating these terms may lead to a temporary or
-permanent ban.
-
-### 3. Temporary Ban
-
-**Community Impact**: A serious violation of community standards, including
-sustained inappropriate behavior.
-
-**Consequence**: A temporary ban from any sort of interaction or public
-communication with the community for a specified period of time. No public or
-private interaction with the people involved, including unsolicited interaction
-with those enforcing the Code of Conduct, is allowed during this period.
-Violating these terms may lead to a permanent ban.
-
-### 4. Permanent Ban
-
-**Community Impact**: Demonstrating a pattern of violation of community
-standards, including sustained inappropriate behavior,  harassment of an
-individual, or aggression toward or disparagement of classes of individuals.
-
-**Consequence**: A permanent ban from any sort of public interaction within
-the community.
-
-## Attribution
-
-This Code of Conduct is adapted from the [Contributor Covenant][homepage],
-version 2.0, available at
-https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
-
-Community Impact Guidelines were inspired by [Mozilla's code of conduct
-enforcement ladder](https://github.com/mozilla/diversity).
-
-[homepage]: https://www.contributor-covenant.org
-
-For answers to common questions about this code of conduct, see the FAQ at
-https://www.contributor-covenant.org/faq. Translations are available at
-https://www.contributor-covenant.org/translations.
--- a/.github/CONTRIBUTING.md
+++ b/.github/CONTRIBUTING.md
@@ -1,76 +0,0 @@
-# Contributing to axolotl
-
-First of all, thank you for your interest in contributing to axolotl! We appreciate the time and effort you're willing to invest in making our project better. This document provides guidelines and information to make the contribution process as smooth as possible.
-
-## Table of Contents
-
- [Code of Conduct](#code-of-conduct)
- [Getting Started](#getting-started)
- [How to Contribute](#how-to-contribute)
-  - [Reporting Bugs](#reporting-bugs)
-  - [Suggesting Enhancements](#suggesting-enhancements)
-  - [Submitting Pull Requests](#submitting-pull-requests)
- [Style Guidelines](#style-guidelines)
-  - [Code Style](#code-style)
-  - [Commit Messages](#commit-messages)
- [Additional Resources](#additional-resources)
-
-## Code of Conductcode
-
-All contributors are expected to adhere to our [Code of Conduct](CODE_OF_CONDUCT.md). Please read it before participating in the axolotl community.
-
-## Getting Started
-
-Bugs? Please check for open issue else create a new [Issue](https://github.com/OpenAccess-AI-Collective/axolotl/issues/new).
-
-PRs are **greatly welcome**!
-
-1. Fork the repository and clone it to your local machine.
-2. Set up the development environment by following the instructions in the [README.md](https://github.com/OpenAccess-AI-Collective/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
-
-# test
-pytest tests/
-```
-
-## How to Contribute
-
-### Reporting Bugs
-
-If you encounter a bug or issue while using axolotl, please open a new issue on the [GitHub Issues](https://github.com/OpenAccess-AI-Collective/axolotl/issues) page. Provide a clear and concise description of the problem, steps to reproduce it, and any relevant error messages or logs.
-
-### Suggesting Enhancements
-
-We welcome ideas for improvements and new features. To suggest an enhancement, open a new issue on the [GitHub Issues](https://github.com/OpenAccess-AI-Collective/axolotl/issues) page. Describe the enhancement in detail, explain the use case, and outline the benefits it would bring to the project.
-
-### Submitting Pull Requests
-
-1. Create a new branch for your feature or bugfix. Use a descriptive name like `feature/your-feature-name` or `fix/your-bugfix-name`.
-2. Make your changes, following the [Style Guidelines](#style-guidelines) below.
-3. Test your changes and ensure that they don't introduce new issues or break existing functionality.
-4. Commit your changes, following the [commit message guidelines](#commit-messages).
-5. Push your branch to your fork on GitHub.
-6. Open a new pull request against the `main` branch of the axolotl repository. Include a clear and concise description of your changes, referencing any related issues.
-
-## Style Guidelines
-
-### Code Style
-
-axolotl uses [{codestyle}]({URLofCodestyle}) as its code style guide. Please ensure that your code follows these guidelines.
-
-### Commit Messages
-
-Write clear and concise commit messages that briefly describe the changes made in each commit. Use the imperative mood and start with a capitalized verb, e.g., "Add new feature" or "Fix bug in function".
-
-## Additional Resources
-
- [GitHub Help](https://help.github.com/)
- [GitHub Pull Request Documentation](https://docs.github.com/en/github/collaborating-with-issues-and-pull-requests)
- [{codestyle}]({URLofCodestyle})
-
-Thank you once again for your interest in contributing to axolotl. We look forward to collaborating with you and creating an even better project together!
--- a/.github/FUNDING.yml
+++ b/.github/FUNDING.yml
@@ -3,11 +3,11 @@
 github: 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: axolotl_ai # Replace with a single Ko-fi username
+ko_fi: # 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: ['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']
+custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']
--- a/.github/ISSUE_TEMPLATE/bug-report.yaml
+++ b/.github/ISSUE_TEMPLATE/bug-report.yaml
@@ -1,112 +0,0 @@
-name: Bug Report
-description: File a bug report
-labels: ["bug", "needs triage"]
-body:
-  - type: markdown
-    attributes:
-      value: |
-        ## Before you start
-        Please **make sure you are on the latest version.**
-        If you encountered the issue after you installed, updated, or reloaded, **please try restarting before reporting the bug**.
-
-  - type: checkboxes
-    id: no-duplicate-issues
-    attributes:
-      label: "Please check that this issue hasn't been reported before."
-      description: "The **Label filters** may help make your search more focussed."
-      options:
-        - label: "I searched previous [Bug Reports](https://github.com/OpenAccess-AI-Collective/axolotl/labels/bug) didn't find any similar reports."
-          required: true
-
-  - type: textarea
-    id: expected
-    attributes:
-      label: Expected Behavior
-      description: Tell us what **should** happen.
-    validations:
-      required: true
-
-  - type: textarea
-    id: what-happened
-    attributes:
-      label: Current behaviour
-      description: |
-        Tell us what happens instead of the expected behavior.
-        Provide stacktrace and/or screenshots.
-    validations:
-      required: true
-
-  - type: textarea
-    id: reproduce
-    attributes:
-      label: Steps to reproduce
-      description: |
-        Which exact steps can a developer take to reproduce the issue?
-        The more detail you provide, the easier it will be to narrow down and fix the bug.
-        Please paste in tasks and/or queries **as text, not screenshots**.
-      placeholder: |
-        Example of the level of detail needed to reproduce any bugs efficiently and reliably.
-        1. Go to the '...' page.
-        2. Click on the '...' button.
-        3. Scroll down to '...'.
-        4. Observe the error.
-    validations:
-      required: true
-
-  - type: textarea
-    id: config
-    attributes:
-      label: Config yaml
-      description: |
-        Please attach the config yaml!
-
-  - type: textarea
-    id: possible-solution
-    attributes:
-      label: Possible solution
-      description: |
-        Not obligatory, but please suggest a fix or reason for the bug, if you have an idea.
-
-
-  - type: checkboxes
-    id: operating-systems
-    attributes:
-      label: Which Operating Systems are you using?
-      description: You may select more than one.
-      options:
-        - label: Linux
-        - label: macOS
-        - label: Windows
-
-  - type: input
-    id: Python-version
-    attributes:
-      label: Python Version
-      description: Which {Programming} version are you using?
-      placeholder: 3.10 / please change accordingly
-    validations:
-      required: true
-
-  - type: input
-    id: axolotl-branch-commit
-    attributes:
-      label: axolotl branch-commit
-      description: On which branch/commit are you?
-      placeholder: main/4d6490b
-    validations:
-      required: true
-
-  - type: checkboxes
-    id: acknowledgements
-    attributes:
-      label: 'Acknowledgements'
-      description: 'Please confirm the following:'
-      options:
-        - label: 'My issue title is concise, descriptive, and in title casing.'
-          required: true
-        - label: 'I have searched the existing issues to make sure this bug has not been reported yet.'
-          required: true
-        - label: 'I am using the latest version of axolotl.'
-          required: true
-        - label: 'I have provided enough information for the maintainers to reproduce and diagnose the issue.'
-          required: true
--- a/.github/ISSUE_TEMPLATE/config.yml
+++ b/.github/ISSUE_TEMPLATE/config.yml
@@ -1,7 +0,0 @@
-blank_issues_enabled: false
-contact_links:
-  - name: Ask a question
-    url: https://github.com/OpenAccess-AI-Collective/axolotl/discussions/categories/q-a
-    about: Ask questions and discuss with other community members
-  - name: Discuss the Project in Discord
-    url: https://discord.gg/HhrNrHJPRb
--- a/.github/ISSUE_TEMPLATE/docs.yml
+++ b/.github/ISSUE_TEMPLATE/docs.yml
@@ -1,46 +0,0 @@
-name: Documentation Improvement / Clarity
-description: Make a suggestion to improve the project documentation.
-labels: ['needs triage', 'docs']
-body:
-  - type: markdown
-    attributes:
-      value: '## :book: Documentation :book:'
-  - type: markdown
-    attributes:
-      value: |
-        * Ask questions in [Discord](https://discord.gg/HhrNrHJPRb).
-        * Before you file an issue read the [Contributing guide](./CONTRIBUTING.md).
-        * Check to make sure someone hasn't already opened a [similar issue](https://github.com/OpenAccess-AI-Collective/axolotl/issues).
-  - type: textarea
-    attributes:
-      label: What piece of documentation is affected?
-      description: Please link to the article you'd like to see updated.
-    validations:
-      required: true
-  - type: textarea
-    attributes:
-      label: What part(s) of the article would you like to see updated?
-      description: |
-        - Give as much detail as you can to help us understand the change you want to see.
-        - Why should the docs be changed? What use cases does it support?
-        - What is the expected outcome?
-    validations:
-      required: true
-  - type: textarea
-    attributes:
-      label: Additional Information
-      description: Add any other context or screenshots about the feature request here.
-    validations:
-      required: false
-  - type: checkboxes
-    id: acknowledgements
-    attributes:
-      label: 'Acknowledgements'
-      description: 'Please confirm the following:'
-      options:
-        - label: 'My issue title is concise, descriptive, and in title casing.'
-          required: true
-        - label: 'I have searched the existing issues to make sure this feature has not been requested yet.'
-          required: true
-        - label: 'I have provided enough information for the maintainers to understand and evaluate this request.'
-          required: true
--- a/.github/ISSUE_TEMPLATE/feature-request.yaml
+++ b/.github/ISSUE_TEMPLATE/feature-request.yaml
@@ -1,63 +0,0 @@
-name: Feature Request / Enhancement
-description: Suggest a new feature or feature enhancement for the project
-labels: ["enhancement", "needs triage"]
-body:
-  - type: checkboxes
-    id: no-duplicate-issues
-    attributes:
-      label: "⚠️ Please check that this feature request hasn't been suggested before."
-      description: "There are two locations for previous feature requests. Please search in both. Thank you. The **Label filters** may help make your search more focussed."
-      options:
-        - label: "I searched previous [Ideas in Discussions](https://github.com/OpenAccess-AI-Collective/axolotl/discussions/categories/ideas) didn't find any similar feature requests."
-          required: true
-        - label: "I searched previous [Issues](https://github.com/OpenAccess-AI-Collective/axolotl/labels/enhancement) didn't find any similar feature requests."
-          required: true
-
-  - type: textarea
-    id: feature-description
-    validations:
-      required: true
-    attributes:
-      label: "🔖 Feature description"
-      description: "A clear and concise description of what the feature request is."
-      placeholder: "You should add ..."
-
-  - type: textarea
-    id: solution
-    validations:
-      required: true
-    attributes:
-      label: "✔️ Solution"
-      description: "A clear and concise description of what you want to happen, and why."
-      placeholder: "In my use-case, ..."
-
-  - type: textarea
-    id: alternatives
-    validations:
-      required: false
-    attributes:
-      label: "❓ Alternatives"
-      description: "A clear and concise description of any alternative solutions or features you've considered."
-      placeholder: "I have considered ..."
-
-  - type: textarea
-    id: additional-context
-    validations:
-      required: false
-    attributes:
-      label: "📝 Additional Context"
-      description: "Add any other context or screenshots about the feature request here."
-      placeholder: "..."
-
-  - type: checkboxes
-    id: acknowledgements
-    attributes:
-      label: 'Acknowledgements'
-      description: 'Please confirm the following:'
-      options:
-        - label: 'My issue title is concise, descriptive, and in title casing.'
-          required: true
-        - label: 'I have searched the existing issues to make sure this feature has not been requested yet.'
-          required: true
-        - label: 'I have provided enough information for the maintainers to understand and evaluate this request.'
-          required: true
--- a/.github/PULL_REQUEST_TEMPLATE.md
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@@ -1,27 +0,0 @@
-<!--- Provide a general summary of your changes in the Title above -->
-
-# Description
-
-<!--- Describe your changes in detail -->
-
-## Motivation and Context
-
-<!--- Why is this change required? What problem does it solve? -->
-<!--- If it fixes an open issue, please link to the issue here. -->
-
-## How has this been tested?
-
-<!--- Please describe in detail how you tested your changes. -->
-<!--- Include details of your testing environment, tests ran to see how -->
-<!--- your change affects other areas of the code, etc. -->
-
-## Screenshots (if appropriate)
-
-## Types of changes
-
-<!--- What types of changes does your code introduce? Put an `x` in all the boxes that apply: -->
-
-## Social Handles (Optional)
-
-<!-- Thanks for submitting a bugfix or enhancement. -->
-<!-- We'd love to show our thanks to you on Twitter & Discord if you provide your handle -->
--- a/.github/SECURITY.md
+++ b/.github/SECURITY.md
@@ -1,9 +0,0 @@
-# Security Policy
-
-## Supported Versions
-
-Due to the nature of the fast development that is happening in this project, only the latest released version can be supported.
-
-## Reporting a Vulnerability
-
-If you find a vulnerability, please contact us on  [Discord](https://discord.gg/xcu3ECkH9a) rather than creating a GitHub issue to allow us some time to fix it before it is a known vulnerability to others.
--- a/.github/SUPPORT.md
+++ b/.github/SUPPORT.md
@@ -1,10 +0,0 @@
-# Support
-
-If you need help with this project or have questions, please:
-
-1. Check the documentation.
-2. Search the existing issues and pull requests.
-3. Create a new issue if your question is not answered or your problem is not solved.
-4. Have a look in the [Discord server](https://discord.gg/HhrNrHJPRb)
-
-Please note that this project is maintained by volunteers who have limited availability. We'll do our best to address your questions and concerns in a timely manner.
--- a/.github/workflows/base.yml
+++ b/.github/workflows/base.yml
@@ -25,16 +25,6 @@ jobs:
            python_version: "3.10"
            pytorch: 2.0.1
            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 9.0+PTX"
-          - cuda: "118"
-            cuda_version: 11.8.0
-            python_version: "3.10"
-            pytorch: 2.1.1
-            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 9.0+PTX"
-          - cuda: "121"
-            cuda_version: 12.1.0
-            python_version: "3.10"
-            pytorch: 2.1.1
-            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 9.0+PTX"
    steps:
      - name: Checkout
        uses: actions/checkout@v3
--- a/.github/workflows/lint.yml
+++ b/.github/workflows/lint.yml
@@ -1,22 +0,0 @@
-name: lint
-on:
-  # check on PRs, and manual triggers
-  pull_request:
-      paths:
-       - '**.py'
-       - 'requirements.txt'
-       - '.github/workflows/*.yml'
-       - "*.md"
-  workflow_dispatch:
-
-jobs:
-  pre-commit:
-    name: pre-commit
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - uses: actions/setup-python@v4
-        with:
-          python-version: "3.9"
-          cache: 'pip' # caching pip dependencies
-      - uses: pre-commit/action@v3.0.0
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -4,6 +4,7 @@ on:
  push:
    branches:
      - "main"
+      - "dev"

 jobs:
  build-axolotl:
@@ -13,70 +14,47 @@ jobs:
      fail-fast: false
      matrix:
        include:
-          - cuda: 118
+          - cuda: cu118
            cuda_version: 11.8.0
            python_version: "3.9"
            pytorch: 2.0.1
            axolotl_extras:
-          - cuda: 118
+          - cuda: cu118
            cuda_version: 11.8.0
            python_version: "3.10"
            pytorch: 2.0.1
            axolotl_extras:
-            is_latest: true
-          - cuda: 118
+          - cuda: cu118
            cuda_version: 11.8.0
-            python_version: "3.10"
-            pytorch: 2.1.1
-            axolotl_extras:
-          - cuda: 121
-            cuda_version: 12.1.0
-            python_version: "3.10"
-            pytorch: 2.1.1
-            axolotl_extras:
-    runs-on: [self-hosted, gpu, docker]
+            python_version: "3.9"
+            pytorch: 2.0.1
+            axolotl_extras: gptq
+    runs-on: self-hosted
    steps:
      - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
      - name: Docker metadata
        id: metadata
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@v3
        with:
          images: winglian/axolotl
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
      - name: Login to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@v2
        with:
          username: ${{ secrets.DOCKERHUB_USERNAME }}
          password: ${{ secrets.DOCKERHUB_TOKEN }}
-      # guidance for testing before pushing: https://docs.docker.com/build/ci/github-actions/test-before-push/
-      - name: Build and export to Docker
-        uses: docker/build-push-action@v5
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+      - name: Build
+        uses: docker/build-push-action@v4
        with:
          context: .
-          load: true
          build-args: |
-            BASE_TAG=${{ github.ref_name }}-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}
-            CUDA=${{ matrix.cuda }}
-            PYTORCH_VERSION=${{ matrix.pytorch }}
+            BASE_TAG=${{ github.ref_name }}-base-py${{ matrix.python_version }}-${{ matrix.cuda }}-${{ matrix.pytorch }}
          file: ./docker/Dockerfile
-          tags: |
-            ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
-            ${{ (matrix.is_latest) && format('{0}-latest', steps.metadata.outputs.tags) || '' }}
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
          labels: ${{ steps.metadata.outputs.labels }}
-      - name: Unit Tests
-        run: |
-          docker run --rm ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }} pytest --ignore=tests/e2e/ /workspace/axolotl/tests/
-      - name: Push to Docker Hub
-        if: github.event_name != 'pull_request'
-        run: |
-          docker push ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
-          latest_tag=${{ (matrix.is_latest) && format('{0}-latest', steps.metadata.outputs.tags) || '' }}
-          if [ -n "$latest_tag" ]; then
-            docker push "$latest_tag"
-          fi
-
  build-axolotl-runpod:
    needs: build-axolotl
    if: github.repository_owner == 'OpenAccess-AI-Collective'
@@ -94,35 +72,29 @@ jobs:
            python_version: "3.10"
            pytorch: 2.0.1
            axolotl_extras:
-            is_latest: true
          - cuda: 118
            cuda_version: 11.8.0
-            python_version: "3.10"
-            pytorch: 2.1.1
-            axolotl_extras:
-          - cuda: 121
-            cuda_version: 12.1.0
-            python_version: "3.10"
-            pytorch: 2.1.1
-            axolotl_extras:
-    runs-on: [self-hosted, gpu, docker]
+            python_version: "3.9"
+            pytorch: 2.0.1
+            axolotl_extras: gptq
+    runs-on: self-hosted
    steps:
      - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
      - name: Docker metadata
        id: metadata
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@v3
        with:
          images: winglian/axolotl-runpod
      - name: Login to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@v2
        with:
          username: ${{ secrets.DOCKERHUB_USERNAME }}
          password: ${{ secrets.DOCKERHUB_TOKEN }}
      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v2
      - name: Build
-        uses: docker/build-push-action@v5
+        uses: docker/build-push-action@v4
        with:
          context: .
          build-args: |
@@ -130,7 +102,5 @@ jobs:
            CUDA=${{ matrix.cuda }}
          file: ./docker/Dockerfile-runpod
          push: ${{ github.event_name != 'pull_request' }}
-          tags: |
-             ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
-             ${{ (matrix.is_latest) && format('{0}-latest', steps.metadata.outputs.tags) || '' }}
+          tags: ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
          labels: ${{ steps.metadata.outputs.labels }}
--- a/.github/workflows/pre-commit.yml
+++ b/.github/workflows/pre-commit.yml
@@ -0,0 +1,16 @@
+name: pre-commit
+
+on:
+  pull_request:
+  push:
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - uses: actions/setup-python@v4
+      with:
+          python-version: "3.9"
+          cache: 'pip' # caching pip dependencies
+    - uses: pre-commit/action@v3.0.0
--- a/.github/workflows/pypi.yml
+++ b/.github/workflows/pypi.yml
@@ -1,45 +0,0 @@
-name: publish pypi
-
-on:
-  push:
-    tags:
-      - '*'
-
-jobs:
-  pypi-publish:
-    name: Upload release to PyPI
-    runs-on: ubuntu-latest
-    environment:
-      name: pypi
-      url: https://pypi.org/p/axolotl
-    permissions:
-      id-token: write  # IMPORTANT: this permission is mandatory for trusted publishing
-    steps:
-      - name: Check out repository code
-        uses: actions/checkout@v3
-
-      - name: Setup Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.10"
-
-      - name: Install dependencies
-        run: |
-          pip3 install wheel
-          pip3 install -e .
-          pip3 install -r requirements-tests.txt
-
-      - name: Extract tag name
-        id: tag
-        run: echo ::set-output name=TAG_NAME::$(echo $GITHUB_REF | cut -d / -f 3)
-
-      - name: Update version in setup.py
-        run: |
-          sed -i -E 's/version="([0-9.]+)",/version="${{ steps.tag.outputs.TAG_NAME }}",/g' setup.py
-
-      - name: Build a binary wheel
-        run: |
-          python setup.py sdist bdist_wheel
-
-      - name: Publish package distributions to PyPI
-        uses: pypa/gh-action-pypi-publish@release/v1
--- a/.github/workflows/tests.yml
+++ b/.github/workflows/tests.yml
@@ -1,39 +1,15 @@
-name: Tests
+name: PyTest
 on:
-  # check on push/merge to main, PRs, and manual triggers
  push:
-    branches:
-      - "main"
-    paths:
-      - '**.py'
-      - 'requirements.txt'
-      - '.github/workflows/*.yml'
  pull_request:
-      paths:
-       - '**.py'
-       - 'requirements.txt'
-       - '.github/workflows/*.yml'
-  workflow_dispatch:

 jobs:
-  pre-commit:
-    name: pre-commit
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - uses: actions/setup-python@v4
-        with:
-          python-version: "3.9"
-          cache: 'pip' # caching pip dependencies
-      - uses: pre-commit/action@v3.0.0
-
-  pytest:
-    name: PyTest
+  test:
    runs-on: ubuntu-latest
    strategy:
      fail-fast: false
      matrix:
-        python_version: ["3.9", "3.10", "3.11"]
+        python_version: ["3.9", "3.10"]
    timeout-minutes: 10

    steps:
@@ -48,61 +24,9 @@ jobs:

      - name: Install dependencies
        run: |
-          pip3 install -U -e .
-          pip3 install -r requirements-tests.txt
+          pip install -e .
+          pip install -r requirements-tests.txt

      - name: Run tests
        run: |
-          pytest --ignore=tests/e2e/ tests/
-
-  docker-e2e-tests:
-    if: github.repository_owner == 'OpenAccess-AI-Collective'
-    # this job needs to be run on self-hosted GPU runners...
-    runs-on: [self-hosted, gpu, docker]
-    timeout-minutes: 30
-    needs: [pre-commit, pytest]
-
-    strategy:
-      fail-fast: false
-      matrix:
-        include:
-          - cuda: 118
-            cuda_version: 11.8.0
-            python_version: "3.10"
-            pytorch: 2.0.1
-          - cuda: 121
-            cuda_version: 12.1.0
-            python_version: "3.10"
-            pytorch: 2.1.1
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      - name: Docker metadata
-        id: metadata
-        uses: docker/metadata-action@v5
-        with:
-          images: winglian/axolotl-tests
-      - name: Build Docker image
-        run: |
-          # Set up build arguments
-          BASE_TAG="main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}"
-          CUDA="${{ matrix.cuda }}"
-          PYTORCH_VERSION="${{ matrix.pytorch }}"
-          # Build the Docker image
-          docker build . \
-            --file ./docker/Dockerfile-tests \
-            --build-arg BASE_TAG=$BASE_TAG \
-            --build-arg CUDA=$CUDA \
-            --build-arg GITHUB_REF=$GITHUB_REF \
-            --build-arg PYTORCH_VERSION=$PYTORCH_VERSION \
-            --tag ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }} \
-            --no-cache
-      - name: Unit Tests w docker image
-        run: |
-          docker run --rm ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }} pytest --ignore=tests/e2e/ /workspace/axolotl/tests/
-      - name: GPU Unit Tests w docker image
-        run: |
-          docker run --privileged --gpus "all" --env WANDB_DISABLED=true --rm ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }} pytest --ignore=tests/e2e/patched/ /workspace/axolotl/tests/e2e/
-      - name: GPU Unit Tests monkeypatched w docker image
-        run: |
-          docker run --privileged --gpus "all" --env WANDB_DISABLED=true --rm ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }} pytest /workspace/axolotl/tests/e2e/patched/
+          pytest tests/
--- a/.gitignore
+++ b/.gitignore
@@ -1,7 +1,5 @@
 **/axolotl.egg-info
 configs
-last_run_prepared/
-.vscode

 # Byte-compiled / optimized / DLL files
 __pycache__/
@@ -163,7 +161,3 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 .idea/
-
-# WandB
-# wandb creates a folder to store logs for training runs
-wandb
--- a/.isort.cfg
+++ b/.isort.cfg
@@ -1,3 +1,2 @@
 [settings]
 profile=black
-known_third_party=wandb
--- a/.mypy.ini
+++ b/.mypy.ini
@@ -8,12 +8,6 @@ ignore_missing_imports = True
 [mypy-axolotl.monkeypatch.*]
 ignore_errors = True

-[mypy-axolotl.models.mixtral.*]
-ignore_errors = True
-
-[mypy-axolotl.models.phi.*]
-ignore_errors = True
-
 [mypy-flash_attn.*]
 ignore_missing_imports = True

@@ -26,9 +20,6 @@ ignore_missing_imports = True
 [mypy-peft]
 ignore_missing_imports = True

-[mypy-wandb]
-ignore_missing_imports = True
-
 [mypy-bitsandbytes]
 ignore_missing_imports = True

--- a/.vscode/README.md
+++ b/.vscode/README.md
@@ -1 +0,0 @@
-See [docs/debugging.md](../docs/debugging.md) for guidance on how to modify these files to debug axolotl with VSCode.
--- a/.vscode/launch.json
+++ b/.vscode/launch.json
@@ -1,34 +0,0 @@
-{
-    // Use IntelliSense to learn about possible attributes.
-    // Hover to view descriptions of existing attributes.
-    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
-    "version": "0.2.0",
-    "configurations": [
-        {
-            "name": "Debug axolotl prompt - sharegpt",
-            "type": "python",
-            "module": "accelerate.commands.launch",
-            "request": "launch",
-            "args": [
-                "-m", "axolotl.cli.train", "dev_sharegpt.yml",
-                // The flags below simplify debugging by overriding the axolotl config
-                // with the debugging tips above.  Modify as needed.
-                "--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
-                "--val_set_size=0",           // disables validation
-                "--sample_packing=False",     // disables sample packing which is necessary for small datasets
-                "--eval_sample_packing=False",// disables sample packing on eval set
-                "--dataset_prepared_path=temp_debug/axolotl_outputs/data", // send data outputs to a temp folder
-                "--output_dir=temp_debug/axolotl_outputs/model" // send model outputs to a temp folder
-                ],
-            "console": "integratedTerminal",      // show output in the integrated terminal
-            "cwd": "${workspaceFolder}/devtools", // set working directory to devtools from the root of the project
-            "justMyCode": true,                   // step through only axolotl code
-            "env": {"CUDA_VISIBLE_DEVICES": "0",  // Since we aren't doing distributed training, we need to limit to one GPU
-                    "HF_HOME": "${workspaceFolder}/devtools/temp_debug/.hf-cache"}, // send HF cache to a temp folder
-            "preLaunchTask": "cleanup-for-dataprep", // delete temp folders (see below)
-        }
-    ]
-}
--- a/.vscode/tasks.json
+++ b/.vscode/tasks.json
@@ -1,27 +0,0 @@
-//this file is used by launch.json
-{
-  "version": "2.0.0",
-  "tasks": [
-    // this task changes into the devtools directory and deletes the temp_debug/axolotl_outputs folder
-    {
-      "label": "delete-outputs",
-      "type": "shell",
-      "command": "rm -rf temp_debug/axolotl_outputs",
-      "options":{ "cwd": "${workspaceFolder}/devtools"},
-      "problemMatcher": []
-    },
-    // this task changes into the devtools directory and deletes the `temp_debug/.hf-cache/datasets` folder
-    {
-      "label": "delete-temp-hf-dataset-cache",
-      "type": "shell",
-      "command": "rm -rf temp_debug/.hf-cache/datasets",
-      "options":{ "cwd": "${workspaceFolder}/devtools"},
-      "problemMatcher": []
-    },
-      // this task combines the two tasks above
-    {
-     "label": "cleanup-for-dataprep",
-     "dependsOn": ["delete-outputs", "delete-temp-hf-dataset-cache"],
-    }
-  ]
-}
--- a/README.md
+++ b/README.md
--- a/data/README.md
+++ b/data/README.md
@@ -0,0 +1,24 @@
+
+## Download some datasets
+```shell
+curl https://raw.githubusercontent.com/tloen/alpaca-lora/main/alpaca_data_gpt4.json -o data/raw/alpaca_data_gpt4.json
+curl https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json -L -o data/raw/vicuna_cleaned.json
+curl https://github.com/teknium1/GPTeacher/blob/main/Instruct/gpt4-instruct-similarity-0.6-dataset.json?raw=true -L -o data/raw/gpt4-instruct-similarity-0.6-dataset.json
+curl https://github.com/teknium1/GPTeacher/blob/main/Roleplay/roleplay-similarity_0.6-instruct-dataset.json?raw=true -L -o data/raw/roleplay-similarity_0.6-instruct-dataset.json
+```
+
+## Convert the JSON data files to JSONL.
+
+```shell
+python3 ./scripts/alpaca_json_to_jsonl.py --file data/alpaca_data_gpt4.json --output data/alpaca_data_gpt4.jsonl
+python3 ./scripts/alpaca_json_to_jsonl.py --file data/raw/vicuna_cleaned.json --output data/vicuna_cleaned.jsonl
+python3 ./scripts/alpaca_json_to_jsonl.py --file data/raw/roleplay-similarity_0.6-instruct-dataset.json --output data/roleplay-similarity_0.6-instruct-dataset.jsonl
+python3 ./scripts/alpaca_json_to_jsonl.py --file data/raw/gpt4-instruct-similarity-0.6-dataset.json --output data/gpt4-instruct-similarity-0.6-dataset.jsonl
+```
+---
+
+Using JSONL makes it easier to subset the data if you want a smaller training set, i.e get 2000 random examples.
+
+```shell
+shuf -n2000 data/vicuna_cleaned.jsonl > data/vicuna_cleaned.subset0.jsonl
+```
--- a/data/raw/.gitignore
+++ b/data/raw/.gitignore
@@ -0,0 +1 @@
+**
--- a/deepspeed/zero1.json
+++ b/deepspeed/zero1.json
@@ -1,31 +0,0 @@
-{
-  "zero_optimization": {
-    "stage": 1,
-    "overlap_comm": true
-  },
-  "bf16": {
-    "enabled": "auto"
-  },
-  "fp16": {
-    "enabled": "auto",
-    "auto_cast": false,
-    "loss_scale": 0,
-    "initial_scale_power": 32,
-    "loss_scale_window": 1000,
-    "hysteresis": 2,
-    "min_loss_scale": 1
-  },
-  "optimizer": {
-    "type": "AdamW",
-    "params": {
-      "lr": "auto",
-      "betas": "auto",
-      "eps": "auto",
-      "weight_decay": "auto"
-    }
-  },
-  "gradient_accumulation_steps": "auto",
-  "train_batch_size": "auto",
-  "train_micro_batch_size_per_gpu": "auto",
-  "wall_clock_breakdown": false
-}
--- a/deepspeed/zero2.json
+++ b/deepspeed/zero2.json
@@ -1,35 +0,0 @@
-{
-  "zero_optimization": {
-    "stage": 2,
-    "offload_optimizer": {
-      "device": "cpu"
-    },
-    "contiguous_gradients": true,
-    "overlap_comm": true
-  },
-  "bf16": {
-    "enabled": "auto"
-  },
-  "fp16": {
-    "enabled": "auto",
-    "auto_cast": false,
-    "loss_scale": 0,
-    "initial_scale_power": 32,
-    "loss_scale_window": 1000,
-    "hysteresis": 2,
-    "min_loss_scale": 1
-  },
-  "optimizer": {
-    "type": "AdamW",
-    "params": {
-      "lr": "auto",
-      "betas": "auto",
-      "eps": "auto",
-      "weight_decay": "auto"
-    }
-  },
-  "gradient_accumulation_steps": "auto",
-  "train_batch_size": "auto",
-  "train_micro_batch_size_per_gpu": "auto",
-  "wall_clock_breakdown": false
-}
--- a/deepspeed/zero3.json
+++ b/deepspeed/zero3.json
@@ -1,6 +1,14 @@
 {
  "zero_optimization": {
    "stage": 3,
+    "offload_optimizer": {
+      "device": "cpu",
+      "pin_memory": true
+    },
+    "offload_param": {
+      "device": "cpu",
+      "pin_memory": true
+    },
    "overlap_comm": true,
    "contiguous_gradients": true,
    "sub_group_size": 0,
@@ -27,12 +35,22 @@
    "type": "AdamW",
    "params": {
      "lr": "auto",
-      "betas": "auto",
-      "eps": "auto",
+      "betas": [
+        0.9,
+        0.95
+      ],
+      "eps": 1e-8,
      "weight_decay": "auto"
    }
  },
-  "gradient_accumulation_steps": "auto",
+  "scheduler": {
+    "type": "WarmupLR",
+    "params": {
+      "warmup_min_lr": "auto",
+      "warmup_max_lr": "auto",
+      "warmup_num_steps": "auto"
+    }
+  },
  "train_batch_size": "auto",
  "train_micro_batch_size_per_gpu": "auto",
  "wall_clock_breakdown": false
--- a/deepspeed/zero3_bf16.json
+++ b/deepspeed/zero3_bf16.json
@@ -1,39 +0,0 @@
-{
-  "zero_optimization": {
-    "stage": 3,
-    "overlap_comm": true,
-    "contiguous_gradients": true,
-    "sub_group_size": 0,
-    "reduce_bucket_size": "auto",
-    "stage3_prefetch_bucket_size": "auto",
-    "stage3_param_persistence_threshold": "auto",
-    "stage3_max_live_parameters": 0,
-    "stage3_max_reuse_distance": 0,
-    "stage3_gather_16bit_weights_on_model_save": true
-  },
-  "bf16": {
-    "enabled": true
-  },
-  "fp16": {
-    "enabled": "auto",
-    "auto_cast": false,
-    "loss_scale": 0,
-    "initial_scale_power": 32,
-    "loss_scale_window": 1000,
-    "hysteresis": 2,
-    "min_loss_scale": 1
-  },
-  "optimizer": {
-    "type": "AdamW",
-    "params": {
-      "lr": "auto",
-      "betas": "auto",
-      "eps": "auto",
-      "weight_decay": "auto"
-    }
-  },
-  "gradient_accumulation_steps": "auto",
-  "train_batch_size": "auto",
-  "train_micro_batch_size_per_gpu": "auto",
-  "wall_clock_breakdown": false
-}
--- a/devtools/README.md
+++ b/devtools/README.md
@@ -1 +0,0 @@
-This directory contains example config files that might be useful for debugging. Please see [docs/debugging.md](../docs/debugging.md) for more information.
--- a/devtools/dev_sharegpt.yml
+++ b/devtools/dev_sharegpt.yml
@@ -1,49 +0,0 @@
-# Example config for debugging the sharegpt prompt format
-base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: true
-load_in_4bit: false
-
-datasets:
-  - path: philschmid/guanaco-sharegpt-style
-    type: sharegpt
-    shards: 10
-val_set_size: 0
-output_dir: temp_debug/axolotl_outputs/model
-dataset_prepared_path: temp_debug/axolotl_outputs/data
-dataset_processes: 1
-
-sequence_len: 4096
-sample_packing: false
-pad_to_sequence_len: true
-
-adapter: lora
-lora_model_dir:
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-micro_batch_size: 1
-num_epochs: 1
-max_steps: 10
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: false
-fp16: true
-tf32: false
-
-gradient_checkpointing: true
-logging_steps: 1
-flash_attention: true
-
-warmup_steps: 10
-weight_decay: 0.0
--- a/docker-compose.yaml
+++ b/docker-compose.yaml
@@ -9,11 +9,6 @@ services:
      - ~/.cache/huggingface/:/root/.cache/huggingface/
    # set environment variables
    environment:
-      # Set environment variables
-      - GIT_AUTHOR_NAME=${GIT_AUTHOR_NAME}
-      - GIT_AUTHOR_EMAIL=${GIT_AUTHOR_EMAIL}
-      - GIT_COMMITTER_NAME=${GIT_COMMITTER_NAME}
-      - GIT_COMMITTER_EMAIL=${GIT_COMMITTER_EMAIL}
      - WANDB_API_KEY=${WANDB_API_KEY}
    deploy:
      resources:
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -5,31 +5,25 @@ ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6+PTX"
 ARG AXOLOTL_EXTRAS=""
 ARG CUDA="118"
 ENV BNB_CUDA_VERSION=$CUDA
-ARG PYTORCH_VERSION="2.0.1"
-
-ENV PYTORCH_VERSION=$PYTORCH_VERSION

 RUN apt-get update && \
-    apt-get install -y --allow-change-held-packages vim curl nano libnccl2 libnccl-dev
+    apt-get install -y vim curl

 WORKDIR /workspace

+RUN pip3 install --force-reinstall "peft @ git+https://github.com/huggingface/peft.git@main"
 RUN git clone --depth=1 https://github.com/OpenAccess-AI-Collective/axolotl.git
-
-WORKDIR /workspace/axolotl
-
 # If AXOLOTL_EXTRAS is set, append it in brackets
-RUN if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
-        pip install -e .[deepspeed,flash-attn,mamba-ssm,$AXOLOTL_EXTRAS]; \
+RUN cd axolotl && \
+    if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
+        pip install -e .[$AXOLOTL_EXTRAS]; \
    else \
-        pip install -e .[deepspeed,flash-attn,mamba-ssm]; \
+        pip install -e .; \
    fi

-# So we can test the Docker image
-RUN pip install pytest
-
 # fix so that git fetch/pull from remote works
-RUN git config remote.origin.fetch "+refs/heads/*:refs/remotes/origin/*" && \
+RUN cd axolotl && \
+    git config remote.origin.fetch "+refs/heads/*:refs/remotes/origin/*" && \
    git config --get remote.origin.fetch

 # helper for huggingface-login cli
--- a/docker/Dockerfile-base
+++ b/docker/Dockerfile-base
@@ -10,28 +10,95 @@ ENV PATH="/root/miniconda3/bin:${PATH}"
 ARG PYTHON_VERSION="3.9"
 ARG PYTORCH_VERSION="2.0.1"
 ARG CUDA="118"
-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

-RUN apt-get update \
-    && apt-get install -y wget git build-essential ninja-build git-lfs libaio-dev && rm -rf /var/lib/apt/lists/* \
-    && wget \
+RUN apt-get update
+RUN apt-get install -y wget git build-essential ninja-build git-lfs libaio-dev && rm -rf /var/lib/apt/lists/*
+
+RUN wget \
    https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh \
    && mkdir /root/.conda \
    && bash Miniconda3-latest-Linux-x86_64.sh -b \
-    && rm -f Miniconda3-latest-Linux-x86_64.sh \
-    && conda create -n "py${PYTHON_VERSION}" python="${PYTHON_VERSION}"
+    && rm -f Miniconda3-latest-Linux-x86_64.sh
+
+RUN conda create -n "py${PYTHON_VERSION}" python="${PYTHON_VERSION}"

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

 WORKDIR /workspace

 RUN python3 -m pip install --upgrade pip && pip3 install packaging && \
-    python3 -m pip install --no-cache-dir -U torch==${PYTORCH_VERSION}+cu${CUDA} deepspeed-kernels --extra-index-url https://download.pytorch.org/whl/cu$CUDA
+    python3 -m pip install --no-cache-dir -U torch==${PYTORCH_VERSION}+cu${CUDA} --extra-index-url https://download.pytorch.org/whl/cu$CUDA

-RUN git lfs install --skip-repo && \
-    pip3 install awscli && \
+
+FROM base-builder AS flash-attn-builder
+
+WORKDIR /workspace
+
+ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
+
+RUN git clone https://github.com/Dao-AILab/flash-attention.git && \
+    cd flash-attention && \
+    git checkout v2.0.4  && \
+    python3 setup.py bdist_wheel && \
+    cd csrc/fused_dense_lib && \
+    python3 setup.py bdist_wheel && \
+    cd ../xentropy && \
+    python3 setup.py bdist_wheel && \
+    cd ../rotary && \
+    python3 setup.py bdist_wheel && \
+    cd ../layer_norm && \
+    python3 setup.py bdist_wheel
+
+FROM base-builder AS deepspeed-builder
+
+ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
+
+WORKDIR /workspace
+
+RUN git clone https://github.com/microsoft/DeepSpeed.git && \
+    cd DeepSpeed && \
+    MAX_CONCURRENCY=8 DS_BUILD_SPARSE_ATTN=0 DS_BUILD_OPS=1 python3 setup.py bdist_wheel
+
+FROM base-builder AS bnb-builder
+
+WORKDIR /workspace
+ARG CUDA="118"
+ENV CUDA=$CUDA
+
+RUN git clone https://github.com/TimDettmers/bitsandbytes.git && \
+    cd bitsandbytes && \
+    CUDA_VERSION=$CUDA make cuda11x && \
+    python setup.py bdist_wheel
+
+FROM base-builder
+
+ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
+ENV TORCH_CUDA_ARCH_LIST=$TORCH_CUDA_ARCH_LIST
+
+# recompile apex
+RUN python3 -m pip uninstall -y apex
+RUN git clone https://github.com/NVIDIA/apex
+#  `MAX_JOBS=1` disables parallel building to avoid cpu memory OOM when building image on GitHub Action (standard) runners
+RUN cd apex && MAX_JOBS=1 python3 -m pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --config-settings "--build-option=--cpp_ext" --config-settings "--build-option=--cuda_ext" ./
+
+RUN mkdir -p /workspace/builds
+COPY --from=bnb-builder /workspace/bitsandbytes /workspace/builds/bitsandbytes
+
+RUN mkdir -p /workspace/wheels/bitsandbytes
+COPY --from=deepspeed-builder /workspace/DeepSpeed/dist/deepspeed-*.whl wheels
+COPY --from=bnb-builder /workspace/bitsandbytes/dist/bitsandbytes-*.whl wheels
+COPY --from=bnb-builder /workspace/bitsandbytes/bitsandbytes/libbitsandbytes*.so wheels/bitsandbytes
+COPY --from=flash-attn-builder /workspace/flash-attention/dist/flash_attn-*.whl wheels
+COPY --from=flash-attn-builder /workspace/flash-attention/csrc/fused_dense_lib/dist/fused_dense_lib-*.whl wheels
+COPY --from=flash-attn-builder /workspace/flash-attention/csrc/xentropy/dist/xentropy_cuda_lib-*.whl wheels
+COPY --from=flash-attn-builder /workspace/flash-attention/csrc/rotary/dist/rotary_emb-*.whl wheels
+COPY --from=flash-attn-builder /workspace/flash-attention/csrc/layer_norm/dist/dropout_layer_norm-*.whl wheels
+
+RUN pip3 install wheels/deepspeed-*.whl wheels/flash_attn-*.whl wheels/fused_dense_lib-*.whl wheels/xentropy_cuda_lib-*.whl wheels/rotary_emb-*.whl wheels/dropout_layer_norm-*.whl
+RUN cd /workspace/builds/bitsandbytes && python3 setup.py install
+RUN git lfs install --skip-repo
+RUN pip3 install awscli && \
    # The base image ships with `pydantic==1.8.2` which is not working
    pip3 install -U --no-cache-dir pydantic==1.10.10
--- a/docker/Dockerfile-runpod
+++ b/docker/Dockerfile-runpod
@@ -4,8 +4,6 @@ FROM winglian/axolotl:$BASE_TAG
 ENV HF_DATASETS_CACHE="/workspace/data/huggingface-cache/datasets"
 ENV HUGGINGFACE_HUB_CACHE="/workspace/data/huggingface-cache/hub"
 ENV TRANSFORMERS_CACHE="/workspace/data/huggingface-cache/hub"
-ENV HF_HOME="/workspace/data/huggingface-cache/hub"
-ENV HF_HUB_ENABLE_HF_TRANSFER="1"

 COPY scripts/runpod-entrypoint.sh /root/runpod-entrypoint.sh

--- a/docker/Dockerfile-tests
+++ b/docker/Dockerfile-tests
@@ -1,40 +0,0 @@
-ARG BASE_TAG=main-base
-FROM winglian/axolotl-base:$BASE_TAG
-
-ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6+PTX"
-ARG AXOLOTL_EXTRAS=""
-ARG CUDA="118"
-ENV BNB_CUDA_VERSION=$CUDA
-ARG PYTORCH_VERSION="2.0.1"
-ARG GITHUB_REF="main"
-
-ENV PYTORCH_VERSION=$PYTORCH_VERSION
-
-RUN apt-get update && \
-    apt-get install -y --allow-change-held-packages vim curl nano libnccl2 libnccl-dev
-
-WORKDIR /workspace
-
-RUN git clone --depth=1 https://github.com/OpenAccess-AI-Collective/axolotl.git
-
-WORKDIR /workspace/axolotl
-
-RUN git fetch origin +$GITHUB_REF && \
-    git checkout FETCH_HEAD
-
-# If AXOLOTL_EXTRAS is set, append it in brackets
-RUN if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
-        pip install -e .[deepspeed,flash-attn,mamba-ssm,$AXOLOTL_EXTRAS]; \
-    else \
-        pip install -e .[deepspeed,flash-attn,mamba-ssm]; \
-    fi
-
-# So we can test the Docker image
-RUN pip install pytest
-
-# 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/docs/debugging.md
+++ b/docs/debugging.md
@@ -1,242 +0,0 @@
-# Debugging Axolotl
-
-This document provides some tips and tricks for debugging Axolotl.  It also provides an example configuration for debugging with VSCode.  A good debugging setup is essential to understanding how Axolotl code works behind the scenes.
-
-## Table of Contents
-
- [General Tips](#general-tips)
- [Debugging with VSCode](#debugging-with-vscode)
-    - [Background](#background)
-    - [Configuration](#configuration)
-    - [Customizing your debugger](#customizing-your-debugger)
-    - [Video Tutorial](#video-tutorial)
- [Debugging With Docker](#debugging-with-docker)
-    - [Setup](#setup)
-    - [Attach To Container](#attach-to-container)
-    - [Video - Attaching To Docker On Remote Host](#video---attaching-to-docker-on-remote-host)
-
-## General Tips
-
-While debugging it's helpful to simplify your test scenario as much as possible.  Here are some tips for doing so:
-
-> [!Important]
-> All of these tips are incorporated into the [example configuration](#configuration) for debugging with VSCode below.
-
-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_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
-    dataset:
-        ...
-        shards: 20
-    ```
-3. **Use a small model**: A good example of a small model is [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0).
-4. **Minimize iteration time**: Make sure the training loop finishes as fast as possible, with these settings.
-    - `micro_batch_size: 1`
-    - `max_steps: 1`
-    - `val_set_size: 0`
-5. **Clear Caches:** Axolotl caches certain steps and so does the underlying HuggingFace trainer.  You may want to clear some of these caches when debugging.
-    - Data preprocessing: When debugging data preprocessing, which includes prompt template formation, you may want to delete the directory set in `dataset_prepared_path:` in your axolotl config.  If you didn't set this value, the default is `last_run_prepared`.
-    - HF Hub: If you are debugging data preprocessing, you should clear the relevant HF cache [HuggingFace cache](https://huggingface.co/docs/datasets/cache), by deleting the appropriate `~/.cache/huggingface/datasets/...` folder(s).
-    - **The recommended approach is to redirect all outputs and caches to a temporary folder and delete selected subfolders before each run.  This is demonstrated in the example configuration below.**
-
-
-## Debugging with VSCode
-
-### Background
-
-The below example shows how to configure VSCode to debug data preprocessing of the `sharegpt` format.  This is the format used when you have the following in your axolotl config:
-
-```yaml
-datasets:
-  - path: <path to your sharegpt formatted dataset> # example on HF Hub: philschmid/guanaco-sharegpt-style
-    type: sharegpt
-```
-
->[!Important]
-> If you are already familiar with advanced VSCode debugging, you can skip the below explanation and look at the files [.vscode/launch.json](../.vscode/launch.json) and [.vscode/tasks.json](../.vscode/tasks.json) for an example configuration.
-
->[!Tip]
-> If you prefer to watch a video, rather than read, you can skip to the [video tutorial](#video-tutorial) below (but doing both is recommended).
-
-### Setup
-
-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 -e '.[flash-attn,deepspeed]'
-```
-
-#### Remote Hosts
-
-If you developing on a remote host, you can easily use VSCode to debug remotely.  To do so, you will need to follow this [remote - SSH guide](https://code.visualstudio.com/docs/remote/ssh).  You can also see the video below on [Docker and Remote SSH debugging](#video---attaching-to-docker-on-remote-host).
-
-```bash
-
-### Configuration
-
-The easiest way to get started is to modify the [.vscode/launch.json](../.vscode/launch.json) file in this project.  This is just an example configuration, so you may need to modify or copy it to suit your needs.
-
-For example, to mimic the command `cd devtools && CUDA_VISIBLE_DEVICES=0 accelerate launch -m axolotl.cli.train dev_sharegpt.yml`, you would use the below configuration[^1].  Note that we add additional flags that override the axolotl config and incorporate the tips above (see the comments). We also set the working directory to `devtools` and set the `env` variable `HF_HOME` to a temporary folder that is later partially deleted.  This is because we want to delete the HF dataset cache before each run in order to ensure that the data preprocessing code is run from scratch.
-
-```jsonc
-// .vscode/launch.json
-{
-    "version": "0.2.0",
-    "configurations": [
-        {
-            "name": "Debug axolotl prompt - sharegpt",
-            "type": "python",
-            "module": "accelerate.commands.launch",
-            "request": "launch",
-            "args": [
-                "-m", "axolotl.cli.train", "dev_sharegpt.yml",
-                // The flags below simplify debugging by overriding the axolotl config
-                // with the debugging tips above.  Modify as needed.
-                "--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
-                "--val_set_size=0",           // disables validation
-                "--sample_packing=False",     // disables sample packing which is necessary for small datasets
-                "--eval_sample_packing=False",// disables sample packing on eval set
-                "--dataset_prepared_path=temp_debug/axolotl_outputs/data", // send data outputs to a temp folder
-                "--output_dir=temp_debug/axolotl_outputs/model" // send model outputs to a temp folder
-                ],
-            "console": "integratedTerminal",      // show output in the integrated terminal
-            "cwd": "${workspaceFolder}/devtools", // set working directory to devtools from the root of the project
-            "justMyCode": true,                   // step through only axolotl code
-            "env": {"CUDA_VISIBLE_DEVICES": "0",  // Since we aren't doing distributed training, we need to limit to one GPU
-                    "HF_HOME": "${workspaceFolder}/devtools/temp_debug/.hf-cache"}, // send HF cache to a temp folder
-            "preLaunchTask": "cleanup-for-dataprep", // delete temp folders (see below)
-        }
-    ]
-}
-```
-
-**Additional notes about this configuration:**
-
- The argument `justMyCode` is set to `true` such that you step through only the axolotl code.  If you want to step into dependencies, set this to `false`.
- The `preLaunchTask`: `cleanup-for-dataprep` is defined in [.vscode/tasks.json](../.vscode/tasks.json) and is used to delete the following folders before debugging, which is essential to ensure that the data pre-processing code is run from scratch:
-    -  `./devtools/temp_debug/axolotl_outputs`
-    - `./devtools/temp_debug/.hf-cache/datasets`
-
->[!Tip]
-> You may not want to delete these folders. For example, if you are debugging model training instead of data pre-processing, you may NOT want to delete the cache or output folders. You may also need to add additional tasks to the `tasks.json` file depending on your use case.
-
-Below is the [./vscode/tasks.json](../.vscode/tasks.json) file that defines the `cleanup-for-dataprep` task.  This task is run before each debugging session when you use the above configuration.  Note how there are two tasks that delete the two folders mentioned above.  The third task `cleanup-for-dataprep` is a composite task that combines the two tasks.  A composite task is necessary because VSCode does not allow you to specify multiple tasks in the `preLaunchTask` argument of the `launch.json` file.
-
-```jsonc
-// .vscode/tasks.json
-// this file is used by launch.json
-{
-    "version": "2.0.0",
-    "tasks": [
-      // this task changes into the devtools directory and deletes the temp_debug/axolotl_outputs folder
-      {
-        "label": "delete-outputs",
-        "type": "shell",
-        "command": "rm -rf temp_debug/axolotl_outputs",
-        "options":{ "cwd": "${workspaceFolder}/devtools"},
-        "problemMatcher": []
-      },
-      // this task changes into the devtools directory and deletes the `temp_debug/.hf-cache/datasets` folder
-      {
-        "label": "delete-temp-hf-dataset-cache",
-        "type": "shell",
-        "command": "rm -rf temp_debug/.hf-cache/datasets",
-        "options":{ "cwd": "${workspaceFolder}/devtools"},
-        "problemMatcher": []
-      },
-        // this task combines the two tasks above
-      {
-       "label": "cleanup-for-dataprep",
-       "dependsOn": ["delete-outputs", "delete-temp-hf-dataset-cache"],
-      }
-    ]
-}
-```
-
-### Customizing your debugger
-
-Your debugging use case may differ from the example above.  The easiest thing to do is to put your own axolotl config in the `devtools` folder and modify the `launch.json` file to use your config.  You may also want to modify the `preLaunchTask` to delete different folders or not delete anything at all.
-
-### Video Tutorial
-
-The following video tutorial walks through the above configuration and demonstrates how to debug with VSCode, (click the image below to watch):
-
-<div style="text-align: center; line-height: 0;">
-
-<a href="https://youtu.be/xUUB11yeMmc" target="_blank"
-title="How to debug Axolotl (for fine tuning LLMs)"><img
-src="https://i.ytimg.com/vi/xUUB11yeMmc/maxresdefault.jpg"
-style="border-radius: 10px; display: block; margin: auto;" width="560" height="315" /></a>
-
-<figcaption style="font-size: smaller;"><a href="https://hamel.dev">Hamel Husain's</a> tutorial: <a href="https://www.youtube.com/watch?v=xUUB11yeMmc">Debugging Axolotl w/VSCode</a></figcaption>
-
-</div>
-<br>
-
-## Debugging With Docker
-
-Using [official Axolotl Docker images](https://hub.docker.com/r/winglian/axolotl/tags) is a great way to debug your code, and is a very popular way to use Axolotl.  Attaching VSCode to Docker takes a few more steps.
-
-### Setup
-
-On the host that is running axolotl (ex: if you are using a remote host), clone the axolotl repo and change your current directory to the root:
-
-```bash
-git clone https://github.com/OpenAccess-AI-Collective/axolotl
-cd axolotl
-```
-
->[!Tip]
-> If you already have axolotl cloned on your host, make sure you have the latest changes and change into the root of the project.
-
-Next, run the desired docker image and mount the current directory. Below is a docker command you can run to do this:[^2]
-
-```bash
-docker run --privileged --gpus '"all"' --shm-size 10g --rm -it --name axolotl --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 --mount type=bind,src="${PWD}",target=/workspace/axolotl -v ${HOME}/.cache/huggingface:/root/.cache/huggingface winglian/axolotl:main-py3.10-cu118-2.0.1
-```
-
->[!Tip]
-> To understand which containers are available, see the [Docker section of the README](../README.md#docker) and the [DockerHub repo](https://hub.docker.com/r/winglian/axolotl/tags).  For details of how the Docker containers are built, see axolotl's [Docker CI builds](../.github/workflows/main.yml).
-
-You will now be in the container.  Next, perform an editable install of Axolotl:
-
-```bash
-pip3 install packaging
-pip3 install -e '.[flash-attn,deepspeed]'
-```
-
-### Attach To Container
-
-Next, if you are using a remote host, [Remote into this host with VSCode](https://code.visualstudio.com/docs/remote/ssh).  If you are using a local host, you can skip this step.
-
-Next, select `Dev Containers: Attach to Running Container...` using the command palette (`CMD + SHIFT + P`) in VSCode.  You will be prompted to select a container to attach to.  Select the container you just created.  You will now be in the container with a working directory that is at the root of the project.  Any changes you make to the code will be reflected both in the container and on the host.
-
-Now you are ready to debug as described above (see [Debugging with VSCode](#debugging-with-vscode)).
-
-### Video - Attaching To Docker On Remote Host
-
-Here is a short video that demonstrates how to attach to a Docker container on a remote host:
-
-<div style="text-align: center; line-height: 0;">
-
-<a href="https://youtu.be/0AuoR7QnHR0" target="_blank"
-title="Debugging Axolotl Part 2: Attaching to Docker on a Remote Host"><img
-src="https://i.ytimg.com/vi/0AuoR7QnHR0/hqdefault.jpg"
-style="border-radius: 10px; display: block; margin: auto;" width="560" height="315" /></a>
-
-<figcaption style="font-size: smaller;"><a href="https://hamel.dev">Hamel Husain's</a> tutorial: <a href="https://youtu.be/0AuoR7QnHR0">Debugging Axolotl Part 2: Attaching to Docker on a Remote Host
-</a></figcaption>
-
-</div>
-<br>
-
-[^1]: The config actually mimics the command `CUDA_VISIBLE_DEVICES=0 python -m accelerate.commands.launch -m axolotl.cli.train devtools/sharegpt.yml`, but this is the same thing.
-
-[^2]: Many of the below flags are recommended best practices by Nvidia when using nvidia-container-toolkit.  You can read more about these flags [here](https://docs.nvidia.com/deeplearning/frameworks/user-guide/index.html).
--- a/docs/faq.md
+++ b/docs/faq.md
@@ -1,18 +0,0 @@
-# Axolotl FAQ's
-
-
-> The trainer stopped and hasn't progressed in several minutes.
-
-Usually an issue with the GPU's communicating with each other. See the [NCCL doc](../docs/nccl.md)
-
-> Exitcode -9
-
-This usually happens when you run out of system RAM.
-
-> Exitcode -7 while using deepspeed
-
-Try upgrading deepspeed w: `pip install -U deepspeed`
-
-> AttributeError: 'DummyOptim' object has no attribute 'step'
-
-You may be using deepspeed with single gpu. Please don't set `deepspeed:` in yaml or cli.
--- a/docs/multi-node.md
+++ b/docs/multi-node.md
@@ -1,45 +0,0 @@
-# Multi Node
-
-You will need to create a configuration for accelerate, either by using `accelerate config` and follow the instructions or you can use one of the preset below:
-
-~/.cache/huggingface/accelerate/default_config.yaml
-```yaml
-compute_environment: LOCAL_MACHINE
-debug: false
-distributed_type: FSDP
-downcast_bf16: 'no'
-machine_rank: 0 # Set to 0 for the main machine, increment by one for other machines
-main_process_ip: 10.0.0.4 # Set to main machine's IP
-main_process_port: 5000
-main_training_function: main
-mixed_precision: bf16
-num_machines: 2 # Change to the number of machines
-num_processes: 4 # That's the total number of GPUs, (for example: if you have 2 machines with 4 GPU, put 8)
-rdzv_backend: static
-same_network: true
-tpu_env: []
-tpu_use_cluster: false
-tpu_use_sudo: false
-use_cpu: false
-```
-
-Configure your model to use FSDP with for example:
-```yaml
-fsdp:
-  - full_shard
-  - auto_wrap
-fsdp_config:
-  fsdp_offload_params: true
-  fsdp_state_dict_type: FULL_STATE_DICT
-  fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer
-```
-
-## Machine configuration
-
-On each machine you need a copy of Axolotl, we suggest using the same commit to ensure compatibility.
-
-You will also need to have the same configuration file for your model on each machine.
-
-On the main machine only, make sure the port you set as `main_process_port` is open in TCP and reachable by other machines.
-
-All you have to do now is launch using accelerate as you would usually do on each machine and voila, the processes will start once you have launched accelerate on every machine.
--- a/docs/multipack.md
+++ b/docs/multipack.md
@@ -1,51 +0,0 @@
-# Multipack
-
-4k context, bsz =4,
-each character represents 256 tokens
-X represents a padding token
-
-```
-   0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5
-[[ A A A A A A A A A A A ]
-   B B B B B B ]
-   C C C C C C C ]
-   D D D D ]]
-
-[[ E E E E E E E E ]
- [ F F F F ]
- [ G G G ]
- [ H H H H ]]
-
-[[ I I I ]
- [ J J J ]
- [ K K K K K]
- [ L L L ]]
-```
-
-after padding to longest input in each step
-```
-   0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5
-[[ A A A A A A A A A A A ]
-   B B B B B B X X X X X X ]
-   C C C C C C C X X X X ]
-   D D D D X X X X X X X ]]
-
-[[ E E E E E E E E ]
- [ F F F F X X X X ]
- [ G G G X X X X X ]
- [ H H H H X X X X ]]
-
-[[ I I I X X ]
- [ J J J X X ]
- [ K K K K K ]
- [ L L L X X ]]
-```
-
-w packing ( note it's the same effective number of tokens per step, but a true bsz of 1)
-```
-   0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5
-[[ A A A A A A A A A A A B B B B B
-   B C C C C C C C D D D D E E E E
-   E E E E F F F F F G G G H H H H
-   I I I J J J J K K K K K L L L X ]]
-```
--- a/docs/nccl.md
+++ b/docs/nccl.md
@@ -1,46 +0,0 @@
-# NCCL
-
-NVIDIA NCCL is a library to facilitate and optimize multi-GPU communication operations, such as broadcast, all-gather, reduce, all-reduce, etc. Broadly, NCCL configuration is highly environment-specific and is configured via several [environment variables](https://docs.nvidia.com/deeplearning/nccl/user-guide/docs/env.html). A common NCCL-related problem occurs when a long-running operation times out causing the training process to abort:
-
-```text
-Watchdog caught collective operation timeout: WorkNCCL(SeqNum=42, OpType=ALLGATHER, Timeout(ms)=1800000) ran for 1806948 milliseconds before timing out.
-```
-
-Often, this timeout will happen after 30 minutes (the default setting) and is accompanied by below-average power consumption with near 100% GPU utilization before the error is raised. Nvidia recommends [disabling PCI access control services (ACS)](https://docs.nvidia.com/deeplearning/nccl/user-guide/docs/troubleshooting.html#pci-access-control-services-acs) as a possible solution if this is available to you.
-
-Forcing cross-GPU communication via [NVLink](https://en.wikipedia.org/wiki/NVLink) may help without increasing timeouts. To verify that your configuration is leveraging NVLink run the following command:
-
-```shell
-nvidia-smi nvlink --status
-```
-
-To force NCCL to use NVLink, simply set this in the environment:
-
-```shell
-export NCCL_P2P_LEVEL=NVL
-```
-
-If NVLink is not available in your environment there are other options for ``NCCL_P2P_LEVEL`` in the table below:
-
-| NCCL_P2P_LEVEL | Description |
-| -------------- | ----------- |
-| PIX | P2P data transfers through no more than a single PCIe bridge. Faster data transfer rates vs to paths involving multiple bridges, but slower compared to direct GPU-to-GPU communication. |
-| PXB | P2P data transfers through multiple PCIe bridges but not going through the PCIe Host Bridge; this path involves a complex routing process, potentially incurring a moderate level of latency. |
-| PHB | P2P data transfers occur over the PCIe and through a PCIe Host Bridge, typically involving the CPU, which can facilitate direct memory access but might introduce additional latency compared to more direct paths (ex PIX, NVL) |
-
-To validate that acceptable data transfer speeds exist for your training job, running [NCCL Tests](https://github.com/NVIDIA/nccl-tests/blob/master/README.md) can help pinpoint bottlenecks, for example:
-
-```shell
-./build/all_reduce_perf -b 8 -e 128M -f 2 -g 3
-```
-
-It can be useful when debugging NCCL communication timeouts to activate additional logging in both PyTorch and NCCL:
-
-```shell
-export NCCL_DEBUG=INFO
-export NCCL_DEBUG_SUBSYS=ALL
-export TORCH_DISTRIBUTED_DEBUG=INFO
-export TORCHELASTIC_ERROR_FILE=/PATH/TO/torcherror.log
-```
-
-Finally, if you believe your training job needs more time you can increase the timeout past 30 minutes by setting the ``ddp_timeout`` value in the Axolotl configuration. See [PyTorch init_process_group](https://pytorch.org/docs/stable/distributed.html#torch.distributed.init_process_group) for documentation on this value.
--- a/docs/rlhf.md
+++ b/docs/rlhf.md
@@ -1,44 +0,0 @@
-# RLHF (Beta)
-
-### Overview
-
-Reinforcement Learning from Human Feedback is a method whereby a language model is optimized from data using human
-feedback. Various methods include, but not limited to:
-
- Proximal Policy Optimization (PPO) (not yet supported in axolotl)
- Direct Preference Optimization (DPO)
- Identity Preference Optimization (IPO)
-
-
-### RLHF using Axolotl
-
-[!IMPORTANT]
-This is a BETA feature and many features are not fully implemented. You are encouraged to open new PRs to improve the integration and functionality.
-
-The various RL training methods are implemented in trl and wrapped via axolotl. Below are various examples with how you can use various preference datasets to train models that use ChatML
-
-#### DPO
-```yaml
-rl: true
-datasets:
-  - path: Intel/orca_dpo_pairs
-    split: train
-    type: intel_apply_chatml
-  - path: argilla/ultrafeedback-binarized-preferences
-    split: train
-    type: argilla_apply_chatml
-```
-
-#### IPO
-```yaml
-rl: ipo
-```
-
-#### Trl autounwrap for peft
-
-Trl supports autounwrapping peft models, so that a ref model does not need to be additionally loaded, leading to less VRAM needed. This is on by default. To turn it off, pass the following config.
-
-```yaml
-# load ref model when adapter training.
-rl_adapter_ref_model: true
-```
--- a/examples/cerebras/btlm-ft.yml
+++ b/examples/cerebras/btlm-ft.yml
@@ -1,89 +0,0 @@
-base_model: cerebras/btlm-3b-8k-base
-model_type: AutoModelForCausalLM
-tokenizer_type: GPT2Tokenizer
-trust_remote_code: true
-tokenizer_use_fast: true
-tokenizer_legacy: true
-
-load_in_8bit: false
-load_in_4bit: false
-strict: false
-push_dataset_to_hub:
-hf_use_auth_token: true
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path: last_prepared_run
-val_set_size: 0.05
-
-adapter:
-lora_model_dir:
-sequence_len: 2048
-max_packed_sequence_len:
-sample_packing: false
-sample_packing_eff_est:
-sample_packing_seq_len_multiplier:
-total_num_tokens:
-
-lora_r:
-lora_alpha:
-lora_dropout:
-lora_target_modules:
-lora_target_linear:
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-output_dir: btlm-out
-gradient_accumulation_steps: 1
-micro_batch_size: 1
-num_epochs: 1
-optimizer: adamw_torch
-adam_beta2: 0.95
-adam_eps: 0.000000001
-max_grad_norm: 1.0
-
-torchdistx_path:
-lr_scheduler: cosine
-lr_quadratic_warmup: true
-learning_rate: 0.000085
-train_on_inputs: true
-group_by_length: false
-bf16: true
-fp16: false
-tf32: true
-
-gradient_checkpointing: false
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-
-xformers_attention:
-flash_attention: true
-sdp_attention:
-flash_optimum:
-
-gptq_groupsize:
-gptq_model_v1:
-
-warmup_steps: 32
-evals_per_epoch: 4
-saves_per_epoch: 1
-save_total_limit:
-
-debug:
-deepspeed:
-weight_decay: 0.1
-special_tokens:
-  pad_token: "<|endoftext|>"
-fsdp:
-#  - full_shard
-#  - auto_wrap
-fsdp_config:
-#  fsdp_state_dict_type: FULL_STATE_DICT
-#  fsdp_transformer_layer_cls_to_wrap: BTLMBlock
--- a/examples/cerebras/qlora.yml
+++ b/examples/cerebras/qlora.yml
@@ -1,4 +1,5 @@
 base_model: cerebras/Cerebras-GPT-1.3B
+base_model_config: cerebras/Cerebras-GPT-1.3B
 load_in_8bit: false
 load_in_4bit: true
 strict: false
@@ -6,8 +7,8 @@ push_dataset_to_hub:
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.01
 adapter: qlora
 lora_model_dir:
 sequence_len: 2048
@@ -24,7 +25,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_name:
+wandb_run_id:
 wandb_log_model:
 output_dir: ./qlora-out
 batch_size: 4
@@ -49,8 +50,8 @@ flash_attention:
 gptq_groupsize:
 gptq_model_v1:
 warmup_steps: 10
-evals_per_epoch: 4
-saves_per_epoch: 1
+eval_steps: 20
+save_steps:
 debug:
 deepspeed:
 weight_decay: 0.1
--- a/examples/code-llama/13b/lora.yml
+++ b/examples/code-llama/13b/lora.yml
@@ -1,67 +0,0 @@
-base_model: codellama/CodeLlama-13b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: CodeLlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: true
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
-output_dir: ./lora-out
-
-sequence_len: 4096
-sample_packing: true
-pad_to_sequence_len: true
-
-adapter: lora
-lora_model_dir:
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 4
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-evals_per_epoch: 4
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/code-llama/13b/qlora.yml
+++ b/examples/code-llama/13b/qlora.yml
@@ -1,69 +0,0 @@
-base_model: codellama/CodeLlama-13b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: CodeLlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
-output_dir: ./qlora-out
-
-adapter: qlora
-lora_model_dir:
-
-sequence_len: 4096
-sample_packing: true
-pad_to_sequence_len: true
-
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 4
-optimizer: paged_adamw_32bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-evals_per_epoch: 4
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/code-llama/34b/lora.yml
+++ b/examples/code-llama/34b/lora.yml
@@ -1,67 +0,0 @@
-base_model: codellama/CodeLlama-34b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: CodeLlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: true
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
-output_dir: ./lora-out
-
-sequence_len: 4096
-sample_packing: true
-pad_to_sequence_len: true
-
-adapter: lora
-lora_model_dir:
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 4
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-evals_per_epoch: 4
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/code-llama/34b/qlora.yml
+++ b/examples/code-llama/34b/qlora.yml
@@ -1,69 +0,0 @@
-base_model: codellama/CodeLlama-34b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: CodeLlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
-output_dir: ./qlora-out
-
-adapter: qlora
-lora_model_dir:
-
-sequence_len: 4096
-sample_packing: true
-pad_to_sequence_len: true
-
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 4
-optimizer: paged_adamw_32bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-evals_per_epoch: 4
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/code-llama/7b/lora.yml
+++ b/examples/code-llama/7b/lora.yml
@@ -1,67 +0,0 @@
-base_model: codellama/CodeLlama-7b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: CodeLlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: true
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
-output_dir: ./lora-out
-
-sequence_len: 4096
-sample_packing: true
-pad_to_sequence_len: true
-
-adapter: lora
-lora_model_dir:
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 4
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-evals_per_epoch: 4
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/code-llama/7b/qlora.yml
+++ b/examples/code-llama/7b/qlora.yml
@@ -1,69 +0,0 @@
-base_model: codellama/CodeLlama-7b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: CodeLlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
-output_dir: ./qlora-out
-
-adapter: qlora
-lora_model_dir:
-
-sequence_len: 4096
-sample_packing: true
-pad_to_sequence_len: true
-
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 4
-optimizer: paged_adamw_32bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-evals_per_epoch: 4
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/code-llama/README.md
+++ b/examples/code-llama/README.md
@@ -1,22 +0,0 @@
-# Overview
-
-This is an example of CodeLLaMA configuration for 7b, 13b and 34b.
-
-The 7b variant fits on any 24GB VRAM GPU and will take up about 17 GB of VRAM during training if using qlora and 20 GB if using lora. On a RTX 4090 it trains 3 epochs of the default dataset in about 15 minutes.
-
-The 13b variant will fit if you change these settings to these values:
-gradient_accumulation_steps: 2
-micro_batch_size: 1
-
-The 34b variant does not fit on 24GB of VRAM - you will need something with +40 gb VRAM that also supports flash attention v2 - A6000 or A100 are good choices.
-
-```shell
-accelerate launch scripts/finetune.py examples/code-llama/[MODEL_SIZE]/qlora.yml
-
-```
-or
-
-```shell
-accelerate launch scripts/finetune.py examples/code-llama/[MODEL_SIZE]/lora.yml
-
-```
--- a/examples/falcon/config-7b-lora.yml
+++ b/examples/falcon/config-7b-lora.yml
@@ -1,8 +1,8 @@
 base_model: tiiuae/falcon-7b
+base_model_config: tiiuae/falcon-7b
 trust_remote_code: true
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
-is_falcon_derived_model: true
 load_in_8bit: true
 load_in_4bit: false
 gptq: false
@@ -11,8 +11,8 @@ push_dataset_to_hub:
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca:chat
-dataset_prepared_path:
-val_set_size: 0.05
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.01
 adapter: lora
 lora_model_dir:
 sequence_len: 2048
@@ -26,7 +26,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_name:
+wandb_run_id:
 wandb_log_model:
 output_dir: ./falcon-7b
 batch_size: 2
@@ -51,8 +51,8 @@ flash_attention:
 gptq_groupsize:
 gptq_model_v1:
 warmup_steps: 40
-evals_per_epoch: 4
-saves_per_epoch: 1
+eval_steps: 5
+save_steps: 43
 debug:
 deepspeed:
 weight_decay: 0.0
--- a/examples/falcon/config-7b-qlora.yml
+++ b/examples/falcon/config-7b-qlora.yml
@@ -1,11 +1,11 @@
 # 1b: tiiuae/falcon-rw-1b
 # 40b: tiiuae/falcon-40b
 base_model: tiiuae/falcon-7b
+base_model_config: tiiuae/falcon-7b
 # required by falcon custom model code: https://huggingface.co/tiiuae/falcon-7b/tree/main
 trust_remote_code: true
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
-is_falcon_derived_model: true
 load_in_8bit: false
 # enable 4bit for QLoRA
 load_in_4bit: true
@@ -17,8 +17,8 @@ datasets:
    data_files:
      - Chain-of-Thought/formatted_cot_data/gsm8k_train.json
    type: "alpaca:chat"
-dataset_prepared_path:
-val_set_size: 0.05
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.01
 # enable QLoRA
 adapter: qlora
 lora_model_dir:
@@ -40,7 +40,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_name:
+wandb_run_id:
 wandb_log_model:
 output_dir: ./qlora-out

@@ -53,7 +53,7 @@ output_dir: ./qlora-out
 # decrease if OOM, increase for max VRAM utilization
 micro_batch_size: 1
 gradient_accumulation_steps: 2
-num_epochs: 4
+num_epochs: 3
 # Optimizer for QLoRA
 optimizer: paged_adamw_32bit
 torchdistx_path:
@@ -80,8 +80,8 @@ flash_attention:
 gptq_groupsize:
 gptq_model_v1:
 warmup_steps: 10
-evals_per_epoch: 4
-saves_per_epoch: 1
+eval_steps: 5
+save_steps: 10
 debug:
 deepspeed:
 weight_decay: 0.000001
--- a/examples/falcon/config-7b.yml
+++ b/examples/falcon/config-7b.yml
@@ -1,8 +1,8 @@
 base_model: tiiuae/falcon-7b
+base_model_config: tiiuae/falcon-7b
 trust_remote_code: true
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
-is_falcon_derived_model: true
 load_in_8bit: false
 load_in_4bit: false
 gptq: false
@@ -11,8 +11,8 @@ push_dataset_to_hub:
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca:chat
-dataset_prepared_path:
-val_set_size: 0.05
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.01
 adapter:
 lora_model_dir:
 sequence_len: 2048
@@ -26,7 +26,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_name:
+wandb_run_id:
 wandb_log_model:
 output_dir: ./falcon-7b
 batch_size: 2
@@ -51,8 +51,8 @@ flash_attention:
 gptq_groupsize:
 gptq_model_v1:
 warmup_steps: 40
-evals_per_epoch: 4
-saves_per_epoch: 1
+eval_steps: 5
+save_steps: 43
 debug:
 deepspeed:
 weight_decay: 0.0
--- a/examples/gptj/qlora.yml
+++ b/examples/gptj/qlora.yml
@@ -1,4 +1,5 @@
 base_model: EleutherAI/gpt-j-6b
+base_model_config: EleutherAI/gpt-j-6b
 load_in_8bit: false
 load_in_4bit: true
 strict: false
@@ -6,8 +7,8 @@ push_dataset_to_hub:
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.01
 adapter: qlora
 lora_model_dir:
 sequence_len: 2048
@@ -21,7 +22,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_name:
+wandb_run_id:
 wandb_log_model:
 output_dir: ./qlora-out
 gradient_accumulation_steps: 2
@@ -46,8 +47,8 @@ flash_attention:
 gptq_groupsize:
 gptq_model_v1:
 warmup_steps: 10
-evals_per_epoch: 4
-saves_per_epoch: 1
+eval_steps: 20
+save_steps:
 debug:
 deepspeed:
 weight_decay: 0.1
--- a/examples/gptq-lora-7b/README.md
+++ b/examples/gptq-lora-7b/README.md
@@ -0,0 +1,8 @@
+# LLaMa 7B using LoRA
+
+This is a good place to start for beginners. This will run on an NVIDIA RTX4090 with no other changes needed.
+
+```shell
+accelerate launch scripts/finetune.py examples/gptq-lora-7b/config.yml
+
+```
--- a/examples/gptq-lora-7b/config.yml
+++ b/examples/gptq-lora-7b/config.yml
@@ -0,0 +1,63 @@
+base_model: Neko-Institute-of-Science/LLaMA-7B-4bit-128g
+base_model_config: Neko-Institute-of-Science/LLaMA-7B-4bit-128g
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+trust_remote_code:
+load_in_8bit: true
+gptq: true
+datasets:
+  - path: vicgalle/alpaca-gpt4
+    type: alpaca
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.02
+adapter:
+lora_model_dir:
+sequence_len: 2048
+max_packed_sequence_len:
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+  - q_proj
+  - v_proj
+lora_fan_in_fan_out: false
+wandb_project: llama-7b-lora-int4
+wandb_entity:
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+output_dir: ./llama-7b-lora-int4
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+num_epochs: 3
+optimizer: adamw_bnb_8bit
+torchdistx_path:
+lr_scheduler: cosine
+learning_rate: 0.0000002
+train_on_inputs: false
+group_by_length: false
+fp16: true
+bf16: false
+tf32: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 5
+xformers_attention:
+flash_attention:
+gradient_checkpointing: true
+gptq_groupsize: 128
+gptq_model_v1: false
+warmup_steps: 20
+eval_steps: 110
+save_steps: 660
+debug:
+deepspeed:
+weight_decay: 0.0001
+fsdp:
+fsdp_config:
+tokens:
+  pad_token: "[PAD]"
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"
--- a/examples/jeopardy-bot/config.yml
+++ b/examples/jeopardy-bot/config.yml
@@ -1,11 +1,12 @@
 base_model: huggyllama/llama-7b
+base_model_config: huggyllama/llama-7b
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
 load_in_8bit: false
 datasets:
  - path: openaccess-ai-collective/jeopardy
    type: jeopardy
-dataset_prepared_path:
+dataset_prepared_path: last_run_prepared
 val_set_size: 0.02
 adapter:
 lora_model_dir:
@@ -19,12 +20,12 @@ lora_fan_in_fan_out: false
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_name:
+wandb_run_id:
 wandb_log_model:
 output_dir: ./jeopardy-bot-7b
 gradient_accumulation_steps: 1
 micro_batch_size: 1
-num_epochs: 4
+num_epochs: 3
 optimizer: adamw_bnb_8bit
 torchdistx_path:
 lr_scheduler: cosine
@@ -42,8 +43,8 @@ flash_attention:
 gptq_groupsize:
 gptq_model_v1:
 warmup_steps: 20
-evals_per_epoch: 4
-saves_per_epoch: 1
+eval_steps: 110
+save_steps: 660
 debug:
 deepspeed:
 weight_decay: 0.1
--- a/examples/llama-2/README.md
+++ b/examples/llama-2/README.md
@@ -9,16 +9,12 @@ gradient_accumulation_steps: 2
 micro_batch_size: 1

 ```shell
-accelerate launch -m axolotl.cli.train examples/llama-2/qlora.yml
+accelerate launch scripts/finetune.py examples/llama-2/qlora.yml
+
 ```
 or

 ```shell
-accelerate launch -m axolotl.cli.train examples/llama-2/lora.yml
-```
+accelerate launch scripts/finetune.py examples/llama-2/lora.yml

-To launch a full finetuning with 16-bit precision:
-
-```shell
-accelerate launch -m axolotl.cli.train examples/llama-2/fft_optimized.yml
 ```
--- a/examples/llama-2/fft_optimized.yml
+++ b/examples/llama-2/fft_optimized.yml
@@ -1,72 +0,0 @@
-base_model: NousResearch/Llama-2-7b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: false
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.05
-output_dir: ./out
-
-sequence_len: 4096
-sample_packing: true
-pad_to_sequence_len: true
-
-adapter:
-lora_model_dir:
-lora_r:
-lora_alpha:
-lora_dropout:
-lora_target_linear:
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 1
-micro_batch_size: 1
-num_epochs: 1
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-flash_attn_cross_entropy: false
-flash_attn_rms_norm: true
-flash_attn_fuse_qkv: false
-flash_attn_fuse_mlp: true
-
-warmup_steps: 100
-evals_per_epoch: 4
-eval_table_size:
-saves_per_epoch: 1
-debug:
-deepspeed: #deepspeed/zero2.json # multi-gpu only
-weight_decay: 0.1
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/llama-2/gptq-lora.yml
+++ b/examples/llama-2/gptq-lora.yml
@@ -1,73 +0,0 @@
-base_model: TheBloke/Llama-2-7B-GPTQ
-is_llama_derived_model: false
-gptq: true
-gptq_disable_exllama: true
-model_type: AutoModelForCausalLM
-tokenizer_type: LlamaTokenizer
-tokenizer_use_fast: true
-tokenizer_legacy: true
-load_in_8bit: false
-load_in_4bit: false
-strict: false
-push_dataset_to_hub:
-hf_use_auth_token: true
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
-adapter: lora
-lora_model_dir:
-sequence_len: 4096
-sample_packing:
-lora_r: 8
-lora_alpha: 32
-lora_dropout: 0.05
-lora_target_modules:
-  - k_proj
-  - o_proj
-  - q_proj
-  - v_proj
-lora_target_linear:
-lora_fan_in_fan_out:
-wandb_project:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-output_dir: ./model-out
-gradient_accumulation_steps: 1
-micro_batch_size: 1
-num_epochs: 4
-optimizer: adamw_torch
-adam_beta2: 0.95
-adam_eps: 0.00001
-max_grad_norm: 1.0
-torchdistx_path:
-lr_scheduler: cosine
-lr_quadratic_warmup: true
-learning_rate: 0.000017
-train_on_inputs: false
-group_by_length: false
-bf16: false
-fp16: false
-float16: true
-tf32: true
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention:
-sdp_attention:
-flash_optimum:
-warmup_steps: 100
-evals_per_epoch: 4
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.1
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/llama-2/lora.yml
+++ b/examples/llama-2/lora.yml
@@ -1,7 +1,7 @@
-base_model: NousResearch/Llama-2-7b-hf
+base_model: meta-llama/Llama-2-7b-hf
+base_model_config: meta-llama/Llama-2-7b-hf
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
-is_llama_derived_model: true

 load_in_8bit: true
 load_in_4bit: false
@@ -10,13 +10,12 @@ strict: false
 datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.01
 output_dir: ./lora-out

 sequence_len: 4096
 sample_packing: true
-pad_to_sequence_len: true

 adapter: lora
 lora_model_dir:
@@ -29,12 +28,12 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_name:
+wandb_run_id:
 wandb_log_model:

 gradient_accumulation_steps: 4
 micro_batch_size: 2
-num_epochs: 4
+num_epochs: 3
 optimizer: adamw_bnb_8bit
 lr_scheduler: cosine
 learning_rate: 0.0002
@@ -54,10 +53,8 @@ xformers_attention:
 flash_attention: true

 warmup_steps: 10
-evals_per_epoch: 4
-eval_table_size:
-eval_table_max_new_tokens: 128
-saves_per_epoch: 1
+eval_steps: 20
+save_steps:
 debug:
 deepspeed:
 weight_decay: 0.0
--- a/examples/llama-2/qlora.yml
+++ b/examples/llama-2/qlora.yml
@@ -1,7 +1,7 @@
-base_model: NousResearch/Llama-2-7b-hf
+base_model: meta-llama/Llama-2-7b-hf
+base_model_config: meta-llama/Llama-2-7b-hf
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
-is_llama_derived_model: true

 load_in_8bit: false
 load_in_4bit: true
@@ -10,8 +10,8 @@ strict: false
 datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.01
 output_dir: ./qlora-out

 adapter: qlora
@@ -19,7 +19,6 @@ lora_model_dir:

 sequence_len: 4096
 sample_packing: true
-pad_to_sequence_len: true

 lora_r: 32
 lora_alpha: 16
@@ -31,12 +30,12 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_name:
+wandb_run_id:
 wandb_log_model:

 gradient_accumulation_steps: 4
 micro_batch_size: 2
-num_epochs: 4
+num_epochs: 3
 optimizer: paged_adamw_32bit
 lr_scheduler: cosine
 learning_rate: 0.0002
@@ -56,9 +55,8 @@ xformers_attention:
 flash_attention: true

 warmup_steps: 10
-evals_per_epoch: 4
-eval_table_size:
-saves_per_epoch: 1
+eval_steps: 20
+save_steps:
 debug:
 deepspeed:
 weight_decay: 0.0
--- a/examples/llama-2/relora.yml
+++ b/examples/llama-2/relora.yml
@@ -1,73 +0,0 @@
-base_model: NousResearch/Llama-2-7b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-
-datasets:
-  - path: teknium/GPT4-LLM-Cleaned
-    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
-output_dir: ./relora-out
-
-adapter: qlora
-lora_model_dir:
-
-sequence_len: 4096
-sample_packing: true
-pad_to_sequence_len: true
-
-lora_r: 8
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-relora_steps: 150
-relora_warmup_steps: 10
-relora_cpu_offload: false
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 4
-num_epochs: 4
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-evals_per_epoch: 4
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/mamba/config.yml
+++ b/examples/mamba/config.yml
@@ -1,61 +0,0 @@
-base_model: state-spaces/mamba-2.8b
-model_type: MambaLMHeadModel
-tokenizer_type: AutoTokenizer
-tokenizer_config: EleutherAI/gpt-neox-20b
-
-load_in_8bit: false
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.0
-output_dir: ./out
-
-sequence_len: 2048
-sample_packing: false
-pad_to_sequence_len: false
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 1
-num_epochs: 2
-optimizer: paged_adamw_8bit
-lr_scheduler: cosine
-learning_rate: 5e-5
-
-train_on_inputs: false
-group_by_length: true
-
-bf16: true
-fp16: false
-tf32: true
-
-gradient_checkpointing: false
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention:
-
-warmup_steps: 10
-evals_per_epoch: 4
-eval_table_size:
-eval_table_max_new_tokens: 128
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-tokens:
-save_safetensors: False
--- a/examples/mistral/README.md
+++ b/examples/mistral/README.md
@@ -1,12 +0,0 @@
-**Mistral 7B** is a language model with a total of 7.3 billion parameters, showcasing a notable performance across a variety of benchmarks.
-
-Fine Tune:
-```shell
-accelerate launch -m axolotl.cli.train examples/mistral/config.yml
-
-```
-
-If you run into CUDA OOM, use deepspeed with config zero2.json:
-```shell
-accelerate launch -m axolotl.cli.train examples/mistral/config.yml --deepspeed deepspeed/zero2.json
-```
--- a/examples/mistral/config.yml
+++ b/examples/mistral/config.yml
@@ -1,62 +0,0 @@
-base_model: mistralai/Mistral-7B-v0.1
-model_type: MistralForCausalLM
-tokenizer_type: LlamaTokenizer
-is_mistral_derived_model: true
-
-load_in_8bit: false
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
-output_dir: ./out
-
-sequence_len: 8192
-sample_packing: true
-pad_to_sequence_len: true
-eval_sample_packing: false
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 4
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.000005
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-evals_per_epoch: 4
-eval_table_size:
-eval_table_max_new_tokens: 128
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/mistral/mixtral.yml
+++ b/examples/mistral/mixtral.yml
@@ -1,91 +0,0 @@
-base_model: mistralai/Mixtral-8x7B-v0.1
-model_type: AutoModelForCausalLM
-tokenizer_type: LlamaTokenizer
-trust_remote_code: true
-
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-
-datasets:
-  - path: tatsu-lab/alpaca
-    type: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.0
-output_dir: ./qlora-out
-
-## You can optionally freeze the entire model and unfreeze a subset of parameters
-unfrozen_parameters:
-#  - lm_head.*
-#  - model.embed_tokens.*
-#  - model.layers.2[0-9]+.block_sparse_moe.gate.*
-#  - model.layers.2[0-9]+.block_sparse_moe.experts.*
-#  - model.layers.3[0-9]+.block_sparse_moe.gate.*
-#  - model.layers.3[0-9]+.block_sparse_moe.experts.*
-
-model_config:
-  output_router_logits: true
-
-adapter: qlora
-lora_model_dir:
-
-sequence_len: 4096
-sample_packing: true
-pad_to_sequence_len: true
-
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-lora_fan_in_fan_out:
-#lora_target_modules:
-#  - gate
-#  - q_proj
-#  - k_proj
-#  - v_proj
-#  - o_proj
-#  - w1
-#  - w2
-#  - w3
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 2
-micro_batch_size: 1
-num_epochs: 1
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-loss_watchdog_threshold: 5.0
-loss_watchdog_patience: 3
-
-warmup_steps: 10
-evals_per_epoch: 4
-eval_table_size:
-eval_table_max_new_tokens: 128
-saves_per_epoch: 1
-debug:
-deepspeed: deepspeed/zero2.json
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
--- a/examples/mistral/qlora.yml
+++ b/examples/mistral/qlora.yml
@@ -1,81 +0,0 @@
-base_model: mistralai/Mistral-7B-v0.1
-model_type: MistralForCausalLM
-tokenizer_type: LlamaTokenizer
-is_mistral_derived_model: true
-
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.1
-output_dir: ./qlora-out
-
-adapter: qlora
-lora_model_dir:
-
-sequence_len: 8192
-sample_packing: true
-pad_to_sequence_len: true
-
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-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: 4
-micro_batch_size: 2
-num_epochs: 1
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-loss_watchdog_threshold: 5.0
-loss_watchdog_patience: 3
-
-warmup_steps: 10
-evals_per_epoch: 4
-eval_table_size:
-eval_table_max_new_tokens: 128
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/mpt-7b/config.yml
+++ b/examples/mpt-7b/config.yml
@@ -1,11 +1,12 @@
 base_model: mosaicml/mpt-7b
+base_model_config: mosaicml/mpt-7b
 tokenizer_type: AutoTokenizer
 trust_remote_code: true  # required for mpt as their model class is not merged into transformers yet
 load_in_8bit: false
 datasets:
  - path: vicgalle/alpaca-gpt4
    type: alpaca
-dataset_prepared_path:
+dataset_prepared_path: last_run_prepared
 val_set_size: 0.02
 adapter:
 lora_model_dir:
@@ -21,12 +22,12 @@ lora_fan_in_fan_out: false
 wandb_project: mpt-alpaca-7b
 wandb_entity:
 wandb_watch:
-wandb_name:
+wandb_run_id:
 wandb_log_model:
 output_dir: ./mpt-alpaca-7b
 gradient_accumulation_steps: 1
 micro_batch_size: 1
-num_epochs: 4
+num_epochs: 3
 optimizer: adamw_bnb_8bit
 torchdistx_path:
 lr_scheduler: cosine
@@ -44,8 +45,8 @@ flash_attention:
 gptq_groupsize:
 gptq_model_v1:
 warmup_steps: 20
-evals_per_epoch: 4
-saves_per_epoch: 1
+eval_steps: 110
+save_steps: 660
 debug:
 deepspeed:
 weight_decay: 0.0001
--- a/examples/openllama-3b/config.yml
+++ b/examples/openllama-3b/config.yml
@@ -1,4 +1,5 @@
-base_model: openlm-research/open_llama_3b_v2
+base_model: openlm-research/open_llama_3b
+base_model_config: openlm-research/open_llama_3b
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
 load_in_8bit: false
@@ -8,12 +9,12 @@ push_dataset_to_hub:
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca
-dataset_prepared_path:
+dataset_prepared_path: last_run_prepared
 val_set_size: 0.02
 adapter:
 lora_model_dir:
-sequence_len: 1024
-sample_packing: true
+sequence_len: 256
+max_packed_sequence_len:
 lora_r:
 lora_alpha:
 lora_dropout:
@@ -23,16 +24,16 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_name:
+wandb_run_id:
 wandb_log_model:
 output_dir: ./openllama-out
 gradient_accumulation_steps: 1
 micro_batch_size: 1
-num_epochs: 4
+num_epochs: 3
 optimizer: adamw_bnb_8bit
 torchdistx_path:
 lr_scheduler: cosine
-learning_rate: 0.000003
+learning_rate: 0.00001
 train_on_inputs: false
 group_by_length: false
 float16: true
@@ -44,13 +45,13 @@ early_stopping_patience:
 resume_from_checkpoint:
 local_rank:
 logging_steps: 1
-xformers_attention:
-flash_attention: true
+xformers_attention: true
+flash_attention:
 gptq_groupsize:
 gptq_model_v1:
-warmup_steps: 20
-evals_per_epoch: 4
-saves_per_epoch: 1
+warmup_steps: 10
+eval_steps: 50
+save_steps:
 debug:
 deepspeed:
 weight_decay: 0.1
--- a/examples/openllama-3b/lora.yml
+++ b/examples/openllama-3b/lora.yml
@@ -1,4 +1,5 @@
-base_model: openlm-research/open_llama_3b_v2
+base_model: openlm-research/open_llama_3b
+base_model_config: openlm-research/open_llama_3b
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
 load_in_8bit: true
@@ -8,12 +9,12 @@ push_dataset_to_hub:
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca
-dataset_prepared_path:
+dataset_prepared_path: last_run_prepared
 val_set_size: 0.02
 adapter: lora
 lora_model_dir:
-sequence_len: 1024
-sample_packing: true
+sequence_len: 256
+max_packed_sequence_len:
 lora_r: 8
 lora_alpha: 16
 lora_dropout: 0.0
@@ -29,12 +30,12 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_name:
+wandb_run_id:
 wandb_log_model:
 output_dir: ./lora-out
-gradient_accumulation_steps: 1
-micro_batch_size: 2
-num_epochs: 4
+batch_size: 16
+micro_batch_size: 4
+num_epochs: 3
 optimizer: adamw_bnb_8bit
 torchdistx_path:
 lr_scheduler: cosine
@@ -49,16 +50,16 @@ early_stopping_patience:
 resume_from_checkpoint:
 local_rank:
 logging_steps: 1
-xformers_attention:
-flash_attention: true
+xformers_attention: true
+flash_attention:
 gptq_groupsize:
 gptq_model_v1:
-warmup_steps: 20
-evals_per_epoch: 4
-saves_per_epoch: 1
+warmup_steps: 10
+eval_steps: 50
+save_steps:
 debug:
 deepspeed:
-weight_decay: 0.1
+weight_decay: 0.0
 fsdp:
 fsdp_config:
 special_tokens:
--- a/examples/openllama-3b/qlora.yml
+++ b/examples/openllama-3b/qlora.yml
@@ -1,4 +1,5 @@
-base_model: openlm-research/open_llama_3b_v2
+base_model: openlm-research/open_llama_3b
+base_model_config: openlm-research/open_llama_3b
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
 load_in_8bit: false
@@ -8,12 +9,12 @@ push_dataset_to_hub:
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.01
 adapter: qlora
 lora_model_dir:
-sequence_len: 1024
-sample_packing: true
+sequence_len: 2048
+max_packed_sequence_len: 2048
 lora_r: 8
 lora_alpha: 32
 lora_dropout: 0.05
@@ -23,36 +24,36 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_name:
+wandb_run_id:
 wandb_log_model:
 output_dir: ./qlora-out
-gradient_accumulation_steps: 1
-micro_batch_size: 2
-num_epochs: 4
+batch_size: 4
+micro_batch_size: 4
+num_epochs: 2
 optimizer: paged_adamw_32bit
 torchdistx_path:
 lr_scheduler: cosine
 learning_rate: 0.0002
 train_on_inputs: false
 group_by_length: false
-bf16: false
-fp16: true
-tf32: false
+bf16: true
+fp16: false
+tf32: true
 gradient_checkpointing: true
 early_stopping_patience:
 resume_from_checkpoint:
 local_rank:
 logging_steps: 1
-xformers_attention:
-flash_attention: true
+xformers_attention: true
+flash_attention:
 gptq_groupsize:
 gptq_model_v1:
-warmup_steps: 20
-evals_per_epoch: 4
-saves_per_epoch: 1
+warmup_steps: 10
+eval_steps: 20
+save_steps:
 debug:
 deepspeed:
-weight_decay: 0.1
+weight_decay: 0.0
 fsdp:
 fsdp_config:
 special_tokens:
--- a/examples/phi/README.md
+++ b/examples/phi/README.md
@@ -1,11 +0,0 @@
-# Phi
-
-Due to some nuances with the phi code, please use deepspeed when training phi for full finetune.
-
-```shell
-accelerate launch -m axolotl.cli.train examples/phi/phi-ft.yml --deepspeed deepspeed/zero1.json
-
-# OR
-
-python -m axolotl.cli.train examples/phi/phi-qlora.yml
-```
--- a/examples/phi/phi-ft.yml
+++ b/examples/phi/phi-ft.yml
@@ -1,74 +0,0 @@
-base_model: microsoft/phi-1_5
-model_type: PhiForCausalLM
-tokenizer_type: AutoTokenizer
-is_llama_derived_model: false
-trust_remote_code: true
-
-load_in_8bit: false
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: garage-bAInd/Open-Platypus
-    type: alpaca
-
-dataset_prepared_path:
-val_set_size: 0.05
-output_dir: ./phi-sft-out
-
-sequence_len: 2048
-sample_packing: true
-pad_to_sequence_len:
-
-adapter:
-lora_model_dir:
-lora_r:
-lora_alpha:
-lora_dropout:
-lora_target_linear:
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 1
-micro_batch_size: 1
-num_epochs: 4
-optimizer: adamw_torch
-adam_beta2: 0.95
-adam_epsilon: 0.00001
-max_grad_norm: 1.0
-lr_scheduler: cosine
-learning_rate: 0.000003
-
-train_on_inputs: false
-group_by_length: true
-bf16: true
-fp16: false
-tf32: true
-
-gradient_checkpointing:
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention:
-
-warmup_steps: 100
-evals_per_epoch: 4
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.1
-fsdp:
-fsdp_config:
-resize_token_embeddings_to_32x: true
-special_tokens:
-  bos_token: "<|endoftext|>"
-  eos_token: "<|endoftext|>"
-  unk_token: "<|endoftext|>"
-  pad_token: "<|endoftext|>"
--- a/examples/phi/phi-qlora.yml
+++ b/examples/phi/phi-qlora.yml
@@ -1,74 +0,0 @@
-base_model: microsoft/phi-1_5
-model_type: AutoModelForCausalLM
-tokenizer_type: AutoTokenizer
-is_llama_derived_model: false
-trust_remote_code: true
-
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-
-datasets:
-  - path: garage-bAInd/Open-Platypus
-    type: alpaca
-
-dataset_prepared_path:
-val_set_size: 0.05
-output_dir: ./phi-sft-out
-
-sequence_len: 1024
-sample_packing: false  # not CURRENTLY compatible with LoRAs
-pad_to_sequence_len:
-
-adapter: qlora
-lora_model_dir:
-lora_r: 64
-lora_alpha: 32
-lora_dropout: 0.05
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 1
-micro_batch_size: 1
-num_epochs: 4
-optimizer: adamw_torch
-adam_beta2: 0.95
-adam_epsilon: 0.00001
-max_grad_norm: 1.0
-lr_scheduler: cosine
-learning_rate: 0.000003
-
-train_on_inputs: false
-group_by_length: true
-bf16: true
-fp16: false
-tf32: true
-
-gradient_checkpointing:
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention:
-
-warmup_steps: 100
-evals_per_epoch: 4
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.1
-fsdp:
-fsdp_config:
-resize_token_embeddings_to_32x: true
-special_tokens:
-  bos_token: "<|endoftext|>"
-  eos_token: "<|endoftext|>"
-  unk_token: "<|endoftext|>"
-  pad_token: "<|endoftext|>"
--- a/examples/phi/phi2-ft.yml
+++ b/examples/phi/phi2-ft.yml
@@ -1,74 +0,0 @@
-base_model: microsoft/phi-2
-model_revision:  834565c  # pin model repo to the previous architecture
-model_type: AutoModelForCausalLM
-tokenizer_type: AutoTokenizer
-trust_remote_code: true
-
-load_in_8bit: false
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: garage-bAInd/Open-Platypus
-    type: alpaca
-
-dataset_prepared_path:
-val_set_size: 0.05
-output_dir: ./phi-sft-out
-
-sequence_len: 2048
-sample_packing: false  # currently unsupported
-pad_to_sequence_len:
-
-adapter:
-lora_model_dir:
-lora_r: 16
-lora_alpha: 32
-lora_dropout: 0.1
-lora_target_linear: true
-lora_fan_in_fan_out:
-lora_modules_to_save:
-  - embd
-  - lm_head
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 1
-micro_batch_size: 1
-num_epochs: 4
-optimizer: paged_adamw_8bit
-adam_beta2: 0.95
-adam_epsilon: 0.00001
-max_grad_norm: 1.0
-lr_scheduler: cosine
-learning_rate: 1e-5
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: true
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 100
-evals_per_epoch: 4
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.1
-fsdp:
-fsdp_config:
-resize_token_embeddings_to_32x: true
-special_tokens:
-  pad_token: "<|endoftext|>"
--- a/examples/pythia-12b/config.yml
+++ b/examples/pythia-12b/config.yml
@@ -1,4 +1,5 @@
 base_model: EleutherAI/pythia-12b-deduped
+base_model_config: EleutherAI/pythia-12b-deduped
 base_model_ignore_patterns: pytorch*  # prefer safetensors
 model_type: GPTNeoXForCausalLM
 tokenizer_type: AutoTokenizer
@@ -9,7 +10,7 @@ device_map: auto
 datasets:
  - path: vicgalle/alpaca-gpt4
    type: alpaca
-dataset_prepared_path:
+dataset_prepared_path: last_run_prepared
 val_set_size: 0.05
 adapter:
 lora_model_dir:
@@ -24,7 +25,7 @@ lora_fan_in_fan_out: true  # pythia/GPTNeoX lora specific
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_name:
+wandb_run_id:
 wandb_log_model:
 output_dir: ./pythia-12b
 gradient_accumulation_steps: 1
@@ -46,3 +47,4 @@ local_rank:
 gradient_checkpointing: true
 fsdp:
 fsdp_config:
+collator_pad_to_longest: true
--- a/examples/pythia/lora.yml
+++ b/examples/pythia/lora.yml
@@ -1,9 +1,10 @@
 base_model: EleutherAI/pythia-1.4b-deduped
+base_model_config: EleutherAI/pythia-1.4b-deduped
 load_in_8bit: true
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca
-dataset_prepared_path:
+dataset_prepared_path: last_run_prepared
 val_set_size: 0.05
 adapter: lora
 lora_model_dir:
@@ -18,20 +19,20 @@ lora_fan_in_fan_out: true  # pythia/GPTNeoX lora specific
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_name:
+wandb_run_id:
 wandb_log_model:
 output_dir: ./lora-alpaca-pythia
 gradient_accumulation_steps: 1
 micro_batch_size: 4
-num_epochs: 4
+num_epochs: 3
 learning_rate: 0.00001
 train_on_inputs: false
 group_by_length: false
-bf16: true
-tf32: true
+bf16: True
+tf32: True
 early_stopping_patience:
 resume_from_checkpoint:
 local_rank:
 weight_decay: 0.1
-evals_per_epoch: 4
+eval_steps: 20
 logging_steps: 1
--- a/examples/qwen/lora.yml
+++ b/examples/qwen/lora.yml
@@ -1,68 +0,0 @@
-base_model: Qwen/Qwen-7B
-model_type: AutoModelForCausalLM
-tokenizer_type: AutoTokenizer
-
-is_qwen_derived_model: true
-trust_remote_code: true
-
-load_in_8bit: true
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
-output_dir: ./lora-out
-
-sequence_len: 2048  # supports up to 8192
-sample_packing: false
-pad_to_sequence_len:
-
-adapter: lora
-lora_model_dir:
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 4
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: false
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention:
-
-warmup_steps: 10
-evals_per_epoch: 4
-eval_table_size:
-eval_table_max_new_tokens: 128
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
--- a/examples/qwen/qlora.yml
+++ b/examples/qwen/qlora.yml
@@ -1,68 +0,0 @@
-base_model: Qwen/Qwen-7B
-model_type: AutoModelForCausalLM
-tokenizer_type: AutoTokenizer
-
-is_qwen_derived_model: true
-trust_remote_code: true
-
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
-output_dir: ./lora-out
-
-sequence_len: 2048  # supports up to 8192
-sample_packing: false
-pad_to_sequence_len:
-
-adapter: qlora
-lora_model_dir:
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 4
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: false
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention:
-
-warmup_steps: 10
-evals_per_epoch: 4
-eval_table_size:
-eval_table_max_new_tokens: 128
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
--- a/examples/redpajama/config-3b.yml
+++ b/examples/redpajama/config-3b.yml
@@ -1,4 +1,5 @@
 base_model: togethercomputer/RedPajama-INCITE-Chat-3B-v1
+base_model_config: togethercomputer/RedPajama-INCITE-Chat-3B-v1
 model_type: GPTNeoXForCausalLM
 tokenizer_type: AutoTokenizer
 trust_remote_code:
@@ -6,7 +7,7 @@ load_in_8bit: false
 datasets:
  - path: vicgalle/alpaca-gpt4
    type: alpaca
-dataset_prepared_path:
+dataset_prepared_path: last_run_prepared
 val_set_size: 0.02
 adapter:
 lora_model_dir:
@@ -22,12 +23,12 @@ lora_fan_in_fan_out: false
 wandb_project: redpajama-alpaca-3b
 wandb_entity:
 wandb_watch:
-wandb_name:
+wandb_run_id:
 wandb_log_model:
 output_dir: ./redpajama-alpaca-3b
 batch_size: 4
 micro_batch_size: 1
-num_epochs: 4
+num_epochs: 3
 optimizer: adamw_bnb_8bit
 torchdistx_path:
 lr_scheduler: cosine
@@ -45,8 +46,8 @@ flash_attention:
 gptq_groupsize:
 gptq_model_v1:
 warmup_steps: 20
-evals_per_epoch: 4
-saves_per_epoch: 1
+eval_steps: 110
+save_steps: 660
 debug:
 deepspeed:
 weight_decay: 0.0001
--- a/examples/replit-3b/config-lora.yml
+++ b/examples/replit-3b/config-lora.yml
@@ -1,10 +1,11 @@
 base_model: replit/replit-code-v1-3b
+base_model_config: replit/replit-code-v1-3b
 trust_remote_code: true
 load_in_8bit: false
 datasets:
  - path: vicgalle/alpaca-gpt4
    type: alpaca
-dataset_prepared_path:
+dataset_prepared_path: last_run_prepared
 val_set_size: 0.05
 adapter: lora
 lora_model_dir:
@@ -21,12 +22,12 @@ lora_fan_in_fan_out:
 wandb_project: lora-replit
 wandb_entity:
 wandb_watch:
-wandb_name:
+wandb_run_id:
 wandb_log_model:
 output_dir: ./lora-replit
 batch_size: 8
 micro_batch_size: 1
-num_epochs: 4
+num_epochs: 3
 optimizer:
 torchdistx_path:
 lr_scheduler:
@@ -45,8 +46,8 @@ flash_attention:
 gptq_groupsize:
 gptq_model_v1:
 warmup_steps: 20
-evals_per_epoch: 4
-saves_per_epoch: 1
+eval_steps: 50
+save_steps:
 debug:
 deepspeed:
 weight_decay: 0
--- a/examples/tiny-llama/README.md
+++ b/examples/tiny-llama/README.md
@@ -1,17 +0,0 @@
-# Overview
-
-This is a simple example of how to finetune TinyLlama1.1B using either lora or qlora:
-
-LoRa:
-
-```
-accelerate launch -m axolotl.cli.train examples/tiny-llama/lora.yml
-```
-
-qLoRa:
-
-```
-accelerate launch -m axolotl.cli.train examples/tiny-llama/qlora.yml
-```
-
-Both take about 10 minutes to complete on a 4090.
--- a/examples/tiny-llama/lora.yml
+++ b/examples/tiny-llama/lora.yml
@@ -1,64 +0,0 @@
-base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: true
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
-output_dir: ./lora-out
-
-sequence_len: 4096
-sample_packing: true
-pad_to_sequence_len: true
-
-adapter: lora
-lora_model_dir:
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 4
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-evals_per_epoch: 4
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
--- a/examples/tiny-llama/pretrain.yml
+++ b/examples/tiny-llama/pretrain.yml
@@ -1,58 +0,0 @@
-base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
-
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: false
-load_in_4bit: false
-strict: false
-
-max_steps: 200
-pretraining_dataset:
-  path: c4
-  name: en
-dataset_prepared_path:
-val_set_size: 0.0
-output_dir: ./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: 4
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-evals_per_epoch:
-eval_table_size:
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
--- a/examples/tiny-llama/qlora.yml
+++ b/examples/tiny-llama/qlora.yml
@@ -1,66 +0,0 @@
-base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path:
-val_set_size: 0.05
-output_dir: ./qlora-out
-
-adapter: qlora
-lora_model_dir:
-
-sequence_len: 4096
-sample_packing: true
-pad_to_sequence_len: true
-
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_name:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 4
-optimizer: paged_adamw_32bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-evals_per_epoch: 4
-saves_per_epoch: 1
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
--- a/examples/xgen-7b/xgen-7b-8k-qlora.yml
+++ b/examples/xgen-7b/xgen-7b-8k-qlora.yml
@@ -1,6 +1,7 @@
 # An example finetuning Saleforce's XGen-7b model with 8k context using qlora
 # on Tim Dettmer's Guanaco dataset.
 base_model: Salesforce/xgen-7b-8k-base
+base_model_config: Salesforce/xgen-7b-8k-base
 trust_remote_code: true
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
@@ -15,8 +16,8 @@ datasets:
    data_files:
      - openassistant_best_replies_train.jsonl
    type: "completion"
-dataset_prepared_path:
-val_set_size: 0.05
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.01
 # enable QLoRA
 adapter: qlora
 lora_model_dir:
@@ -38,7 +39,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_name:
+wandb_run_id:
 wandb_log_model:
 output_dir: ./qlora-out

@@ -51,7 +52,7 @@ output_dir: ./qlora-out
 # decrease if OOM, increase for max VRAM utilization
 micro_batch_size: 1
 gradient_accumulation_steps: 1
-num_epochs: 4
+num_epochs: 3
 # Optimizer for QLoRA
 optimizer: paged_adamw_32bit
 torchdistx_path:
@@ -78,8 +79,8 @@ flash_attention:
 gptq_groupsize:
 gptq_model_v1:
 warmup_steps: 10
-evals_per_epoch: 4
-saves_per_epoch: 1
+eval_steps: 50
+save_steps: 50
 debug:
 deepspeed:
 weight_decay: 0.0
--- a/examples/yi-34B-chat/README.md
+++ b/examples/yi-34B-chat/README.md
@@ -1,5 +0,0 @@
-# Overview
-
-This is an example of a Yi-34B-Chat configuration. It demonstrates that it is possible to finetune a 34B model on a GPU with 24GB of VRAM.
-
-Tested on an RTX 4090 with `python -m axolotl.cli.train examples/mistral/qlora.yml`, a single epoch of finetuning on the alpaca dataset using qlora runs in 47 mins, using 97% of available memory.
--- a/examples/yi-34B-chat/qlora.yml
+++ b/examples/yi-34B-chat/qlora.yml
@@ -1,76 +0,0 @@
-base_model: 01-ai/Yi-34B-Chat
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-is_mistral_derived_model: false
-is_llama_derived_model: true
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-sequence_len: 1024
-bf16: true
-fp16: false
-tf32: false
-flash_attention: true
-special_tokens:
-  bos_token: "<|startoftext|>"
-  eos_token: "<|endoftext|>"
-  unk_token: "<unk>"
-
-# Data
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-warmup_steps: 10
-
-# Iterations
-num_epochs: 1
-
-# Evaluation
-val_set_size: 0.1
-evals_per_epoch: 5
-eval_table_size:
-eval_table_max_new_tokens: 128
-eval_sample_packing: false
-eval_batch_size: 1
-
-# LoRA
-output_dir: ./qlora-out
-adapter: qlora
-lora_model_dir:
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-lora_fan_in_fan_out:
-lora_target_modules:
-
-# Sampling
-sample_packing: false
-pad_to_sequence_len: false
-
-# Batching
-gradient_accumulation_steps: 4
-micro_batch_size: 1
-gradient_checkpointing: true
-
-# wandb
-wandb_project:
-
-# Optimizer
-optimizer: paged_adamw_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-# Misc
-train_on_inputs: false
-group_by_length: false
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-debug:
-deepspeed:
-weight_decay: 0
-fsdp:
-fsdp_config:
--- a/image/sticker_fixed.png
+++ b/image/sticker_fixed.png
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,26 +1,20 @@
--extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
-packaging==23.2
-peft==0.7.0
-transformers @ git+https://github.com/huggingface/transformers.git@3cefac1d974db5e2825a0cb2b842883a628be7a0
-tokenizers==0.15.0
+peft @ git+https://github.com/huggingface/peft.git
+transformers @ git+https://github.com/huggingface/transformers.git
 bitsandbytes>=0.41.1
-accelerate @ git+https://github.com/huggingface/accelerate.git@0d2280dadc6a93413a5496613b7fdda3a4d2551b
-deepspeed
+accelerate @ git+https://github.com/huggingface/accelerate@2a289f6108e77a77a4efffb3f6316bc98538413b
 addict
 fire
-PyYAML>=6.0
-datasets>=2.15.0
-flash-attn==2.3.3
+PyYAML==6.0
+datasets
+accelerate>=0.19.0
 sentencepiece
 wandb
 einops
-xformers==0.0.22
-optimum==1.13.2
+xformers
+optimum
 hf_transfer
-colorama
 numba
-numpy>=1.24.4
-mlflow
+numpy==1.24.4
 # qlora things
 bert-score==0.3.13
 evaluate==0.4.0
@@ -28,16 +22,3 @@ rouge-score==0.1.2
 scipy
 scikit-learn==1.2.2
 pynvml
-art
-fschat==0.2.34
-gradio==3.50.2
-tensorboard
-
-mamba-ssm==1.1.1
-
-# remote filesystems
-s3fs
-gcsfs
-# adlfs
-
-trl>=0.7.9
--- a/scripts/alpaca_json_to_jsonl.py
+++ b/scripts/alpaca_json_to_jsonl.py
@@ -0,0 +1,52 @@
+"""Module to convert json file to jsonl"""
+
+import os
+import sys
+from pathlib import Path
+from typing import Optional, Union
+
+import fire
+
+from axolotl.convert import (
+    FileReader,
+    FileWriter,
+    JsonlSerializer,
+    JsonParser,
+    JsonToJsonlConverter,
+    StdoutWriter,
+)
+from axolotl.logging_config import configure_logging
+
+configure_logging()
+
+# add src to the pythonpath so we don't need to pip install this
+project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
+src_dir = os.path.join(project_root, "src")
+sys.path.insert(0, src_dir)
+
+
+def main(
+    file: Path,
+    output: Optional[Path] = None,
+    to_stdout: Optional[bool] = False,
+):
+    """
+    Convert a json file to jsonl
+    """
+
+    file_reader = FileReader()
+    writer: Union[StdoutWriter, FileWriter]
+    if to_stdout or output is None:
+        writer = StdoutWriter()
+    else:
+        writer = FileWriter(output)
+    json_parser = JsonParser()
+    jsonl_serializer = JsonlSerializer()
+
+    converter = JsonToJsonlConverter(file_reader, writer, json_parser, jsonl_serializer)
+
+    converter.convert(file, output)
+
+
+if __name__ == "__main__":
+    fire.Fire(main)
--- a/scripts/finetune.py
+++ b/scripts/finetune.py
@@ -1,52 +1,338 @@
 """Prepare and train a model on a dataset. Can also infer from a model or merge lora"""
+
+import importlib
 import logging
+import os
+import random
+import signal
+import sys
 from pathlib import Path
+from typing import Any, Dict, List, Optional, Union

 import fire
-import transformers
+import torch
+import yaml

-from axolotl.cli import (
-    check_accelerate_default_config,
-    check_user_token,
-    do_inference,
-    do_merge_lora,
-    load_cfg,
-    load_datasets,
-    print_axolotl_text_art,
+# add src to the pythonpath so we don't need to pip install this
+from optimum.bettertransformer import BetterTransformer
+from transformers import GenerationConfig, TextStreamer
+
+from axolotl.logging_config import configure_logging
+from axolotl.utils.config import normalize_config, validate_config
+from axolotl.utils.data import load_prepare_datasets, load_pretraining_dataset
+from axolotl.utils.dict import DictDefault
+from axolotl.utils.distributed import barrier, is_main_process
+from axolotl.utils.models import load_model, load_tokenizer
+from axolotl.utils.tokenization import check_dataset_labels
+from axolotl.utils.trainer import (
+    calculate_total_num_steps,
+    process_datasets_for_packing,
+    setup_trainer,
 )
-from axolotl.cli.shard import shard
-from axolotl.common.cli import TrainerCliArgs
-from axolotl.train import train
+from axolotl.utils.wandb import setup_wandb_env_vars

-LOG = logging.getLogger("axolotl.scripts.finetune")
+project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
+src_dir = os.path.join(project_root, "src")
+sys.path.insert(0, src_dir)
+
+configure_logging()
+LOG = logging.getLogger("axolotl.scripts")


-def do_cli(config: Path = Path("examples/"), **kwargs):
-    print_axolotl_text_art()
-    LOG.warning(
-        str(
-            PendingDeprecationWarning(
-                "scripts/finetune.py will be replaced with calling axolotl.cli.train"
-            )
+DEFAULT_DATASET_PREPARED_PATH = "last_run_prepared"
+os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
+
+
+def get_multi_line_input() -> Optional[str]:
+    print("Give me an instruction (Ctrl + D to finish): ")
+    instruction = ""
+    for line in sys.stdin:
+        instruction += line  # pylint: disable=consider-using-join
+    # instruction = pathlib.Path("/proc/self/fd/0").read_text()
+    return instruction
+
+
+def do_inference(cfg, model, tokenizer, prompter: Optional[str]):
+    default_tokens = {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>"}
+
+    for token, symbol in default_tokens.items():
+        # If the token isn't already specified in the config, add it
+        if not (cfg.special_tokens and token in cfg.special_tokens):
+            tokenizer.add_special_tokens({token: symbol})
+
+    prompter_module = None
+    if prompter:
+        prompter_module = getattr(
+            importlib.import_module("axolotl.prompters"), prompter
        )
+
+    if cfg.landmark_attention:
+        from axolotl.monkeypatch.llama_landmark_attn import set_model_mem_id
+
+        set_model_mem_id(model, tokenizer)
+        model.set_mem_cache_args(
+            max_seq_len=255, mem_freq=50, top_k=5, max_cache_size=None
+        )
+
+    while True:
+        print("=" * 80)
+        # support for multiline inputs
+        instruction = get_multi_line_input()
+        if not instruction:
+            return
+        if prompter_module:
+            prompt: str = next(
+                prompter_module().build_prompt(instruction=instruction.strip("\n"))
+            )
+        else:
+            prompt = instruction.strip()
+        batch = tokenizer(prompt, return_tensors="pt", add_special_tokens=True)
+
+        print("=" * 40)
+        model.eval()
+        with torch.no_grad():
+            generation_config = GenerationConfig(
+                repetition_penalty=1.1,
+                max_new_tokens=1024,
+                temperature=0.9,
+                top_p=0.95,
+                top_k=40,
+                bos_token_id=tokenizer.bos_token_id,
+                eos_token_id=tokenizer.eos_token_id,
+                pad_token_id=tokenizer.pad_token_id,
+                do_sample=True,
+                use_cache=True,
+                return_dict_in_generate=True,
+                output_attentions=False,
+                output_hidden_states=False,
+                output_scores=False,
+            )
+            streamer = TextStreamer(tokenizer)
+            generated = model.generate(
+                inputs=batch["input_ids"].to(cfg.device),
+                generation_config=generation_config,
+                streamer=streamer,
+            )
+        print("=" * 40)
+        print(tokenizer.decode(generated["sequences"].cpu().tolist()[0]))
+
+
+def choose_config(path: Path):
+    yaml_files = list(path.glob("*.yml"))
+
+    if not yaml_files:
+        raise ValueError(
+            "No YAML config files found in the specified directory. Are you using a .yml extension?"
+        )
+
+    print("Choose a YAML file:")
+    for idx, file in enumerate(yaml_files):
+        print(f"{idx + 1}. {file}")
+
+    chosen_file = None
+    while chosen_file is None:
+        try:
+            choice = int(input("Enter the number of your choice: "))
+            if 1 <= choice <= len(yaml_files):
+                chosen_file = yaml_files[choice - 1]
+            else:
+                print("Invalid choice. Please choose a number from the list.")
+        except ValueError:
+            print("Invalid input. Please enter a number.")
+
+    return chosen_file
+
+
+def check_not_in(list1: List[str], list2: Union[Dict[str, Any], List[str]]) -> bool:
+    return not any(el in list2 for el in list1)
+
+
+def train(
+    config: Path = Path("configs/"),
+    prepare_ds_only: bool = False,
+    **kwargs,
+):
+    if Path(config).is_dir():
+        config = choose_config(config)
+
+    # load the config from the yaml file
+    with open(config, encoding="utf-8") as file:
+        cfg: DictDefault = DictDefault(yaml.safe_load(file))
+    # if there are any options passed in the cli, if it is something that seems valid from the yaml,
+    # then overwrite the value
+    cfg_keys = cfg.keys()
+    for k, _ in kwargs.items():
+        # if not strict, allow writing to cfg even if it's not in the yml already
+        if k in cfg_keys or not cfg.strict:
+            # handle booleans
+            if isinstance(cfg[k], bool):
+                cfg[k] = bool(kwargs[k])
+            else:
+                cfg[k] = kwargs[k]
+
+    validate_config(cfg)
+
+    normalize_config(cfg)
+
+    setup_wandb_env_vars(cfg)
+
+    # load the tokenizer first
+    LOG.info(f"loading tokenizer... {cfg.tokenizer_config or cfg.base_model_config}")
+    tokenizer = load_tokenizer(cfg)
+
+    if (
+        check_not_in(["shard", "merge_lora"], kwargs) and not cfg.inference
+    ):  # don't need to load dataset for these
+        if not cfg.pretraining_dataset:
+            train_dataset, eval_dataset = load_prepare_datasets(
+                tokenizer, cfg, DEFAULT_DATASET_PREPARED_PATH
+            )
+        else:
+            train_dataset = load_pretraining_dataset(
+                cfg.pretraining_dataset,
+                tokenizer,
+                max_tokens=cfg.sequence_len,
+                seed=cfg.seed or 42,
+            )
+            # https://discuss.huggingface.co/t/how-to-use-huggingface-trainer-streaming-datasets-without-wrapping-it-with-torchdatas-iterablewrapper/25230
+            train_dataset = train_dataset.with_format("torch")
+            eval_dataset = None
+
+        if is_main_process():
+            # process on rank 0 first so it gets cached so other ranks load from cache
+            train_dataset, eval_dataset = process_datasets_for_packing(
+                cfg, train_dataset, eval_dataset
+            )
+        barrier()
+        if not is_main_process():
+            train_dataset, eval_dataset = process_datasets_for_packing(
+                cfg, train_dataset, eval_dataset
+            )
+        barrier()
+        if cfg.max_steps:
+            total_num_steps = min(
+                calculate_total_num_steps(cfg, train_dataset, tokenizer), cfg.max_steps
+            )
+            LOG.info(f"Maximum number of steps set at {total_num_steps}")
+        else:
+            total_num_steps = calculate_total_num_steps(cfg, train_dataset, tokenizer)
+
+    if cfg.debug or "debug" in kwargs:
+        LOG.info("check_dataset_labels...")
+        check_dataset_labels(
+            train_dataset.select(
+                [random.randrange(0, len(train_dataset) - 1) for _ in range(5)]  # nosec
+            ),
+            tokenizer,
+        )
+
+    if prepare_ds_only:
+        LOG.info("Finished preparing dataset. Exiting...")
+        return
+
+    # Load the model and tokenizer
+    LOG.info("loading model and (optionally) peft_config...")
+    model, peft_config = load_model(cfg, tokenizer)
+
+    safe_serialization = cfg.save_safetensors is True
+
+    if "merge_lora" in kwargs and cfg.adapter is not None:
+        LOG.info("running merge of LoRA with base model")
+        model = model.merge_and_unload()
+        model.to(dtype=torch.float16)
+
+        if cfg.local_rank == 0:
+            LOG.info("saving merged model")
+            model.save_pretrained(
+                str(Path(cfg.output_dir) / "merged"),
+                safe_serialization=safe_serialization,
+            )
+            tokenizer.save_pretrained(str(Path(cfg.output_dir) / "merged"))
+        return
+
+    if cfg.inference:
+        LOG.info("calling do_inference function")
+        prompter: Optional[str] = "AlpacaPrompter"
+        if "prompter" in kwargs:
+            if kwargs["prompter"] == "None":
+                prompter = None
+            else:
+                prompter = kwargs["prompter"]
+        do_inference(cfg, model, tokenizer, prompter=prompter)
+        return
+
+    if "shard" in kwargs:
+        model.save_pretrained(cfg.output_dir, safe_serialization=safe_serialization)
+        return
+
+    trainer = setup_trainer(
+        cfg, train_dataset, eval_dataset, model, tokenizer, total_num_steps
    )
-    parsed_cfg = load_cfg(config, **kwargs)
-    check_accelerate_default_config()
-    check_user_token()
-    parser = transformers.HfArgumentParser((TrainerCliArgs))
-    parsed_cli_args, _ = parser.parse_args_into_dataclasses(
-        return_remaining_strings=True
-    )
-    if parsed_cli_args.inference:
-        do_inference(cfg=parsed_cfg, cli_args=parsed_cli_args)
-    elif parsed_cli_args.merge_lora:
-        do_merge_lora(cfg=parsed_cfg, cli_args=parsed_cli_args)
-    elif parsed_cli_args.shard:
-        shard(cfg=parsed_cfg, cli_args=parsed_cli_args)
+
+    model.config.use_cache = False
+
+    if torch.__version__ >= "2" and sys.platform != "win32":
+        LOG.info("Compiling torch model")
+        model = torch.compile(model)
+
+    # go ahead and presave, so we have the adapter config available to inspect
+    if peft_config:
+        LOG.info(f"Pre-saving adapter config to {cfg.output_dir}")
+        peft_config.save_pretrained(cfg.output_dir)
+
+    # In case we want to stop early with ctrl+c, this is a nice to have to save the pretrained model
+    if cfg.local_rank == 0:
+
+        def terminate_handler(_, __, model):
+            if cfg.flash_optimum:
+                model = BetterTransformer.reverse(model)
+            model.save_pretrained(cfg.output_dir, safe_serialization=safe_serialization)
+            sys.exit(0)
+
+        signal.signal(
+            signal.SIGINT, lambda signum, frame: terminate_handler(signum, frame, model)
+        )
+
+    LOG.info("Starting trainer...")
+    if cfg.group_by_length:
+        LOG.info("hang tight... sorting dataset for group_by_length")
+    resume_from_checkpoint = cfg.resume_from_checkpoint
+    if cfg.resume_from_checkpoint is None and cfg.auto_resume_from_checkpoints:
+        possible_checkpoints = [
+            str(cp) for cp in Path(cfg.output_dir).glob("checkpoint-*")
+        ]
+        if len(possible_checkpoints) > 0:
+            sorted_paths = sorted(
+                possible_checkpoints,
+                key=lambda path: int(path.split("-")[-1]),
+            )
+            resume_from_checkpoint = sorted_paths[-1]
+            LOG.info(
+                f"Using Auto-resume functionality to start with checkpoint at {resume_from_checkpoint}"
+            )
+
+    if not Path(cfg.output_dir).is_dir():
+        os.makedirs(cfg.output_dir, exist_ok=True)
+    tokenizer.save_pretrained(cfg.output_dir)
+    if cfg.flash_optimum:
+        with torch.backends.cuda.sdp_kernel(
+            enable_flash=True, enable_math=True, enable_mem_efficient=True
+        ):
+            trainer.train(resume_from_checkpoint=resume_from_checkpoint)
    else:
-        dataset_meta = load_datasets(cfg=parsed_cfg, cli_args=parsed_cli_args)
-        train(cfg=parsed_cfg, cli_args=parsed_cli_args, dataset_meta=dataset_meta)
+        trainer.train(resume_from_checkpoint=resume_from_checkpoint)
+
+    LOG.info(f"Training Completed!!! Saving pre-trained model to {cfg.output_dir}")
+
+    # TODO do we need this fix? https://huggingface.co/docs/accelerate/usage_guides/fsdp#saving-and-loading
+    # only save on rank 0, otherwise it corrupts output on multi-GPU when multiple processes attempt to write the same file
+    if cfg.fsdp:
+        trainer.save_model(cfg.output_dir)
+    elif cfg.local_rank == 0:
+        if cfg.flash_optimum:
+            model = BetterTransformer.reverse(model)
+        model.save_pretrained(cfg.output_dir, safe_serialization=safe_serialization)


 if __name__ == "__main__":
-    fire.Fire(do_cli)
+    fire.Fire(train)
--- a/setup.py
+++ b/setup.py
@@ -1,68 +1,33 @@
 """setup.py for axolotl"""

-from importlib.metadata import PackageNotFoundError, version
-
 from setuptools import find_packages, setup

-
-def parse_requirements():
-    _install_requires = []
-    _dependency_links = []
-    with open("./requirements.txt", encoding="utf-8") as requirements_file:
-        lines = [r.strip() for r in requirements_file.readlines()]
-        for line in lines:
-            is_extras = (
-                "flash-attn" in line
-                or "flash-attention" in line
-                or "deepspeed" in line
-                or "mamba-ssm" in line
-            )
-            if line.startswith("--extra-index-url"):
-                # Handle custom index URLs
-                _, url = line.split()
-                _dependency_links.append(url)
-            elif not is_extras and line and line[0] != "#":
-                # Handle standard packages
-                _install_requires.append(line)
-
-    try:
-        torch_version = version("torch")
-        if torch_version.startswith("2.1.1"):
-            _install_requires.pop(_install_requires.index("xformers==0.0.22"))
-            _install_requires.append("xformers==0.0.23")
-    except PackageNotFoundError:
-        pass
-
-    return _install_requires, _dependency_links
-
-
-install_requires, dependency_links = parse_requirements()
-
+install_requires = []
+with open("./requirements.txt", encoding="utf-8") as requirements_file:
+    # don't include peft yet until we check the int4
+    # need to manually install peft for now...
+    reqs = [r.strip() for r in requirements_file.readlines() if "peft" not in r]
+    reqs = [r for r in reqs if r and r[0] != "#"]
+    for r in reqs:
+        install_requires.append(r)

 setup(
    name="axolotl",
-    version="0.3.0",
-    description="LLM Trainer",
-    long_description="Axolotl is a tool designed to streamline the fine-tuning of various AI models, offering support for multiple configurations and architectures.",
+    version="0.1",
+    description="You know you're going to axolotl questions",
    package_dir={"": "src"},
    packages=find_packages(),
    install_requires=install_requires,
-    dependency_links=dependency_links,
    extras_require={
-        "flash-attn": [
-            "flash-attn==2.3.3",
+        "gptq": [
+            "alpaca_lora_4bit @ git+https://github.com/winglian/alpaca_lora_4bit.git@setup_pip",
        ],
-        "fused-dense-lib": [
-            "fused-dense-lib  @ git+https://github.com/Dao-AILab/flash-attention@v2.3.3#subdirectory=csrc/fused_dense_lib",
+        "gptq_triton": [
+            "alpaca_lora_4bit[triton] @ git+https://github.com/winglian/alpaca_lora_4bit.git@setup_pip",
        ],
-        "deepspeed": [
+        "extras": [
+            "flash-attn",
            "deepspeed",
        ],
-        "mamba-ssm": [
-            "mamba-ssm==1.0.1",
-        ],
-        "auto-gptq": [
-            "auto-gptq==0.5.1",
-        ],
    },
 )
--- a/src/axolotl/cli/init.py
+++ b/src/axolotl/cli/init.py
@@ -1,446 +0,0 @@
-"""Prepare and train a model on a dataset. Can also infer from a model or merge lora"""
-
-import importlib
-import logging
-import math
-import os
-import random
-import sys
-from pathlib import Path
-from threading import Thread
-from typing import Any, Dict, List, Optional, Union
-
-import gradio as gr
-import torch
-import yaml
-
-# add src to the pythonpath so we don't need to pip install this
-from accelerate.commands.config import config_args
-from art import text2art
-from datasets import concatenate_datasets, load_dataset
-from huggingface_hub import HfApi
-from huggingface_hub.utils import LocalTokenNotFoundError
-from transformers import GenerationConfig, TextIteratorStreamer, TextStreamer
-
-from axolotl.common.cli import TrainerCliArgs, load_model_and_tokenizer
-from axolotl.logging_config import configure_logging
-from axolotl.train import TrainDatasetMeta
-from axolotl.utils.config import (
-    normalize_cfg_datasets,
-    normalize_config,
-    validate_config,
-)
-from axolotl.utils.data import prepare_dataset
-from axolotl.utils.dict import DictDefault
-from axolotl.utils.distributed import is_main_process
-from axolotl.utils.mlflow_ import setup_mlflow_env_vars
-from axolotl.utils.models import load_tokenizer
-from axolotl.utils.tokenization import check_dataset_labels
-from axolotl.utils.trainer import prepare_optim_env
-from axolotl.utils.wandb_ import setup_wandb_env_vars
-
-project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
-src_dir = os.path.join(project_root, "src")
-sys.path.insert(0, src_dir)
-
-configure_logging()
-LOG = logging.getLogger("axolotl.scripts")
-
-os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
-
-
-def print_axolotl_text_art(suffix=None):
-    font = "nancyj"
-    ascii_text = "  axolotl"
-    if suffix:
-        ascii_text += f"  x  {suffix}"
-    ascii_art = text2art(ascii_text, font=font)
-
-    if is_main_process():
-        print(ascii_art)
-
-
-def get_multi_line_input() -> Optional[str]:
-    print("Give me an instruction (Ctrl + D to submit): ")
-    instruction = ""
-    for line in sys.stdin:
-        instruction += line  # pylint: disable=consider-using-join
-    # instruction = pathlib.Path("/proc/self/fd/0").read_text()
-    return instruction
-
-
-def do_merge_lora(
-    *,
-    cfg: DictDefault,
-    cli_args: TrainerCliArgs,
-):
-    model, tokenizer = load_model_and_tokenizer(cfg=cfg, cli_args=cli_args)
-    safe_serialization = cfg.save_safetensors is True
-
-    LOG.info("running merge of LoRA with base model")
-    model = model.merge_and_unload(progressbar=True)
-    model.to(dtype=cfg.torch_dtype)
-
-    if cfg.local_rank == 0:
-        LOG.info(f"saving merged model to: {str(Path(cfg.output_dir) / 'merged')}")
-        model.save_pretrained(
-            str(Path(cfg.output_dir) / "merged"),
-            safe_serialization=safe_serialization,
-            progressbar=True,
-        )
-        tokenizer.save_pretrained(str(Path(cfg.output_dir) / "merged"))
-
-
-def do_inference(
-    *,
-    cfg: DictDefault,
-    cli_args: TrainerCliArgs,
-):
-    model, tokenizer = load_model_and_tokenizer(cfg=cfg, cli_args=cli_args)
-    prompter = cli_args.prompter
-    default_tokens = {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>"}
-
-    for token, symbol in default_tokens.items():
-        # If the token isn't already specified in the config, add it
-        if not (cfg.special_tokens and token in cfg.special_tokens):
-            tokenizer.add_special_tokens({token: symbol})
-
-    prompter_module = None
-    if prompter:
-        prompter_module = getattr(
-            importlib.import_module("axolotl.prompters"), prompter
-        )
-
-    model = model.to(cfg.device, dtype=cfg.torch_dtype)
-
-    while True:
-        print("=" * 80)
-        # support for multiline inputs
-        instruction = get_multi_line_input()
-        if not instruction:
-            return
-        if prompter_module:
-            prompt: str = next(
-                prompter_module().build_prompt(instruction=instruction.strip("\n"))
-            )
-        else:
-            prompt = instruction.strip()
-        batch = tokenizer(prompt, return_tensors="pt", add_special_tokens=True)
-
-        print("=" * 40)
-        model.eval()
-        with torch.no_grad():
-            generation_config = GenerationConfig(
-                repetition_penalty=1.1,
-                max_new_tokens=1024,
-                temperature=0.9,
-                top_p=0.95,
-                top_k=40,
-                bos_token_id=tokenizer.bos_token_id,
-                eos_token_id=tokenizer.eos_token_id,
-                pad_token_id=tokenizer.pad_token_id,
-                do_sample=True,
-                use_cache=True,
-                return_dict_in_generate=True,
-                output_attentions=False,
-                output_hidden_states=False,
-                output_scores=False,
-            )
-            streamer = TextStreamer(tokenizer)
-            generated = model.generate(
-                inputs=batch["input_ids"].to(cfg.device),
-                generation_config=generation_config,
-                streamer=streamer,
-            )
-        print("=" * 40)
-        print(tokenizer.decode(generated["sequences"].cpu().tolist()[0]))
-
-
-def do_inference_gradio(
-    *,
-    cfg: DictDefault,
-    cli_args: TrainerCliArgs,
-):
-    model, tokenizer = load_model_and_tokenizer(cfg=cfg, cli_args=cli_args)
-    prompter = cli_args.prompter
-    default_tokens = {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>"}
-
-    for token, symbol in default_tokens.items():
-        # If the token isn't already specified in the config, add it
-        if not (cfg.special_tokens and token in cfg.special_tokens):
-            tokenizer.add_special_tokens({token: symbol})
-
-    prompter_module = None
-    if prompter:
-        prompter_module = getattr(
-            importlib.import_module("axolotl.prompters"), prompter
-        )
-
-    model = model.to(cfg.device, dtype=cfg.torch_dtype)
-
-    def generate(instruction):
-        if not instruction:
-            return
-        if prompter_module:
-            # pylint: disable=stop-iteration-return
-            prompt: str = next(
-                prompter_module().build_prompt(instruction=instruction.strip("\n"))
-            )
-        else:
-            prompt = instruction.strip()
-        batch = tokenizer(prompt, return_tensors="pt", add_special_tokens=True)
-
-        model.eval()
-        with torch.no_grad():
-            generation_config = GenerationConfig(
-                repetition_penalty=1.1,
-                max_new_tokens=1024,
-                temperature=0.9,
-                top_p=0.95,
-                top_k=40,
-                bos_token_id=tokenizer.bos_token_id,
-                eos_token_id=tokenizer.eos_token_id,
-                pad_token_id=tokenizer.pad_token_id,
-                do_sample=True,
-                use_cache=True,
-                return_dict_in_generate=True,
-                output_attentions=False,
-                output_hidden_states=False,
-                output_scores=False,
-            )
-            streamer = TextIteratorStreamer(tokenizer)
-            generation_kwargs = {
-                "inputs": batch["input_ids"].to(cfg.device),
-                "generation_config": generation_config,
-                "streamer": streamer,
-            }
-
-            thread = Thread(target=model.generate, kwargs=generation_kwargs)
-            thread.start()
-
-            all_text = ""
-
-            for new_text in streamer:
-                all_text += new_text
-                yield all_text
-
-    demo = gr.Interface(
-        fn=generate,
-        inputs="textbox",
-        outputs="text",
-        title=cfg.get("gradio_title", "Axolotl Gradio Interface"),
-    )
-    demo.queue().launch(show_api=False, share=True)
-
-
-def choose_config(path: Path):
-    yaml_files = list(path.glob("*.yml"))
-
-    if not yaml_files:
-        raise ValueError(
-            "No YAML config files found in the specified directory. Are you using a .yml extension?"
-        )
-
-    if len(yaml_files) == 1:
-        print(f"Using default YAML file '{yaml_files[0]}'")
-        return yaml_files[0]
-
-    print("Choose a YAML file:")
-    for idx, file in enumerate(yaml_files):
-        print(f"{idx + 1}. {file}")
-
-    chosen_file = None
-    while chosen_file is None:
-        try:
-            choice = int(input("Enter the number of your choice: "))
-            if 1 <= choice <= len(yaml_files):
-                chosen_file = yaml_files[choice - 1]
-            else:
-                print("Invalid choice. Please choose a number from the list.")
-        except ValueError:
-            print("Invalid input. Please enter a number.")
-
-    return chosen_file
-
-
-def check_not_in(list1: List[str], list2: Union[Dict[str, Any], List[str]]) -> bool:
-    return not any(el in list2 for el in list1)
-
-
-def load_cfg(config: Path = Path("examples/"), **kwargs):
-    if Path(config).is_dir():
-        config = choose_config(config)
-
-    # load the config from the yaml file
-    with open(config, encoding="utf-8") as file:
-        cfg: DictDefault = DictDefault(yaml.safe_load(file))
-    cfg.axolotl_config_path = config
-    # if there are any options passed in the cli, if it is something that seems valid from the yaml,
-    # then overwrite the value
-    cfg_keys = cfg.keys()
-    for k, _ in kwargs.items():
-        # if not strict, allow writing to cfg even if it's not in the yml already
-        if k in cfg_keys or not cfg.strict:
-            # handle booleans
-            if isinstance(cfg[k], bool):
-                cfg[k] = bool(kwargs[k])
-            else:
-                cfg[k] = kwargs[k]
-
-    validate_config(cfg)
-
-    prepare_optim_env(cfg)
-
-    normalize_config(cfg)
-
-    normalize_cfg_datasets(cfg)
-
-    setup_wandb_env_vars(cfg)
-
-    setup_mlflow_env_vars(cfg)
-
-    return cfg
-
-
-def load_datasets(
-    *,
-    cfg: DictDefault,
-    cli_args: TrainerCliArgs,
-) -> TrainDatasetMeta:
-    tokenizer = load_tokenizer(cfg)
-
-    train_dataset, eval_dataset, total_num_steps, prompters = prepare_dataset(
-        cfg, tokenizer
-    )
-
-    if cli_args.debug or cfg.debug:
-        LOG.info("check_dataset_labels...")
-        check_dataset_labels(
-            train_dataset.select(
-                [
-                    random.randrange(0, len(train_dataset) - 1)  # nosec
-                    for _ in range(cli_args.debug_num_examples)
-                ]
-            ),
-            tokenizer,
-            num_examples=cli_args.debug_num_examples,
-            text_only=cli_args.debug_text_only,
-        )
-
-        LOG.info("printing prompters...")
-        for prompter in prompters:
-            LOG.info(prompter)
-
-    return TrainDatasetMeta(
-        train_dataset=train_dataset,
-        eval_dataset=eval_dataset,
-        total_num_steps=total_num_steps,
-    )
-
-
-def load_rl_datasets(
-    *,
-    cfg: DictDefault,
-    cli_args: TrainerCliArgs,  # pylint: disable=unused-argument
-) -> TrainDatasetMeta:
-    train_datasets: List[Any] = []
-    for i, ds_cfg in enumerate(cfg.datasets):
-        train_datasets.insert(i, load_dataset(ds_cfg["path"], split=ds_cfg["split"]))
-    # eval_dataset = load_dataset(
-    #     cfg.test_datasets[0]["path"], split=cfg.test_datasets[0]["split"]
-    # )
-    eval_dataset = None
-
-    def argilla_apply_chatml(sample):  # pylint: disable=possibly-unused-variable
-        if "system" in sample and sample["system"]:
-            sample["prompt"] = (
-                f"<|im_start|>system\n{sample['system']}<|im_end|>\n"
-                f"<|im_start|>user\n{sample['instruction']}<|im_end|>\n<|im_start|>assistant\n"
-            )
-        else:
-            sample[
-                "prompt"
-            ] = f"<|im_start|>user\n{sample['instruction']}<|im_end|>\n<|im_start|>assistant\n"
-        sample["chosen"] = f"{sample['chosen_response']}<|im_end|>"
-        sample["rejected"] = f"{sample['rejected_response']}<|im_end|>"
-        return sample
-
-    def intel_apply_chatml(sample):  # pylint: disable=possibly-unused-variable
-        if "system" in sample and sample["system"]:
-            sample["prompt"] = (
-                f"<|im_start|>system\n{sample['system']}<|im_end|>\n"
-                f"<|im_start|>user\n{sample['question']}<|im_end|>\n<|im_start|>assistant\n"
-            )
-        else:
-            sample[
-                "prompt"
-            ] = f"<|im_start|>user\n{sample['question']}<|im_end|>\n<|im_start|>assistant\n"
-        sample["chosen"] = f"{sample['chosen']}<|im_end|>"
-        sample["rejected"] = f"{sample['rejected']}<|im_end|>"
-        return sample
-
-    def apply_chatml(sample):  # pylint: disable=possibly-unused-variable
-        if "system" in sample and sample["system"]:
-            sample["prompt"] = (
-                f"<|im_start|>system\n{sample['system']}<|im_end|>\n"
-                f"<|im_start|>user\n{sample['prompt']}<|im_end|>\n<|im_start|>assistant\n"
-            )
-        else:
-            sample[
-                "prompt"
-            ] = f"<|im_start|>user\n{sample['prompt']}<|im_end|>\n<|im_start|>assistant\n"
-        sample["chosen"] = f"{sample['chosen']}<|im_end|>"
-        sample["rejected"] = f"{sample['rejected']}<|im_end|>"
-        return sample
-
-    def ultra_apply_chatml(sample):  # pylint: disable=possibly-unused-variable
-        if "system" in sample and sample["system"]:
-            sample["prompt"] = (
-                f"<|im_start|>system\n{sample['system']}<|im_end|>\n"
-                f"<|im_start|>user\n{sample['prompt']}<|im_end|>\n<|im_start|>assistant\n"
-            )
-        else:
-            sample[
-                "prompt"
-            ] = f"<|im_start|>user\n{sample['prompt']}<|im_end|>\n<|im_start|>assistant\n"
-        sample["chosen"] = f"{sample['chosen'][1]['content']}<|im_end|>"
-        sample["rejected"] = f"{sample['rejected'][1]['content']}<|im_end|>"
-        return sample
-
-    for i, data_set in enumerate(train_datasets):
-        _type = cfg.datasets[i]["type"]
-        ds_type_fn = locals()[_type]
-        train_datasets[i] = data_set.map(ds_type_fn)
-    train_dataset = concatenate_datasets(train_datasets)
-
-    # eval_dataset = eval_dataset.map(intel_apply_chatml)
-
-    total_num_steps = int(
-        math.ceil(len(train_dataset) * cfg.num_epochs / cfg.batch_size)
-    )
-
-    return TrainDatasetMeta(
-        train_dataset=train_dataset,
-        eval_dataset=eval_dataset,
-        total_num_steps=total_num_steps,
-    )
-
-
-def check_accelerate_default_config():
-    if Path(config_args.default_yaml_config_file).exists():
-        LOG.warning(
-            f"accelerate config file found at {config_args.default_yaml_config_file}. This can lead to unexpected errors"
-        )
-
-
-def check_user_token():
-    # Verify if token is valid
-    api = HfApi()
-    try:
-        user_info = api.whoami()
-        return bool(user_info)
-    except LocalTokenNotFoundError:
-        LOG.warning(
-            "Error verifying HuggingFace token. Remember to log in using `huggingface-cli login` and get your access token from https://huggingface.co/settings/tokens if you want to use gated models or datasets."
-        )
-        return False
--- a/src/axolotl/cli/inference.py
+++ b/src/axolotl/cli/inference.py
@@ -1,36 +0,0 @@
-"""
-CLI to run inference on a trained model
-"""
-from pathlib import Path
-
-import fire
-import transformers
-
-from axolotl.cli import (
-    do_inference,
-    do_inference_gradio,
-    load_cfg,
-    print_axolotl_text_art,
-)
-from axolotl.common.cli import TrainerCliArgs
-
-
-def do_cli(config: Path = Path("examples/"), gradio=False, **kwargs):
-    # pylint: disable=duplicate-code
-    print_axolotl_text_art()
-    parsed_cfg = load_cfg(config, **kwargs)
-    parsed_cfg.sample_packing = False
-    parser = transformers.HfArgumentParser((TrainerCliArgs))
-    parsed_cli_args, _ = parser.parse_args_into_dataclasses(
-        return_remaining_strings=True
-    )
-    parsed_cli_args.inference = True
-
-    if gradio:
-        do_inference_gradio(cfg=parsed_cfg, cli_args=parsed_cli_args)
-    else:
-        do_inference(cfg=parsed_cfg, cli_args=parsed_cli_args)
-
-
-if __name__ == "__main__":
-    fire.Fire(do_cli)
--- a/src/axolotl/cli/merge_lora.py
+++ b/src/axolotl/cli/merge_lora.py
@@ -1,46 +0,0 @@
-"""
-CLI to run merge a trained LoRA into a base model
-"""
-from pathlib import Path
-
-import fire
-import transformers
-
-from axolotl.cli import do_merge_lora, load_cfg, print_axolotl_text_art
-from axolotl.common.cli import TrainerCliArgs
-
-
-def do_cli(config: Path = Path("examples/"), **kwargs):
-    # pylint: disable=duplicate-code
-    print_axolotl_text_art()
-    parser = transformers.HfArgumentParser((TrainerCliArgs))
-    parsed_cli_args, _ = parser.parse_args_into_dataclasses(
-        return_remaining_strings=True
-    )
-    parsed_cli_args.merge_lora = True
-
-    parsed_cfg = load_cfg(
-        config,
-        merge_lora=True,
-        load_in_8bit=False,
-        load_in_4bit=False,
-        flash_attention=False,
-        **kwargs,
-    )
-
-    if not parsed_cfg.lora_model_dir and parsed_cfg.output_dir:
-        parsed_cfg.lora_model_dir = parsed_cfg.output_dir
-    if not Path(parsed_cfg.lora_model_dir).exists():
-        raise ValueError(
-            f"Target directory for merge: `{parsed_cfg.lora_model_dir}` does not exist."
-        )
-
-    parsed_cfg.load_in_4bit = False
-    parsed_cfg.load_in_8bit = False
-    parsed_cfg.flash_attention = False
-
-    do_merge_lora(cfg=parsed_cfg, cli_args=parsed_cli_args)
-
-
-if __name__ == "__main__":
-    fire.Fire(do_cli)
--- a/src/axolotl/cli/preprocess.py
+++ b/src/axolotl/cli/preprocess.py
@@ -1,54 +0,0 @@
-"""
-CLI to run training on a model
-"""
-import logging
-from pathlib import Path
-
-import fire
-import transformers
-from colorama import Fore
-
-from axolotl.cli import (
-    check_accelerate_default_config,
-    check_user_token,
-    load_cfg,
-    load_datasets,
-    print_axolotl_text_art,
-)
-from axolotl.common.cli import PreprocessCliArgs
-from axolotl.common.const import DEFAULT_DATASET_PREPARED_PATH
-
-LOG = logging.getLogger("axolotl.cli.preprocess")
-
-
-def do_cli(config: Path = Path("examples/"), **kwargs):
-    # pylint: disable=duplicate-code
-    print_axolotl_text_art()
-    parsed_cfg = load_cfg(config, **kwargs)
-    check_accelerate_default_config()
-    check_user_token()
-    parser = transformers.HfArgumentParser((PreprocessCliArgs))
-    parsed_cli_args, _ = parser.parse_args_into_dataclasses(
-        return_remaining_strings=True
-    )
-
-    if not parsed_cfg.dataset_prepared_path:
-        msg = (
-            Fore.RED
-            + "preprocess CLI called without dataset_prepared_path set, "
-            + f"using default path: {DEFAULT_DATASET_PREPARED_PATH}"
-            + Fore.RESET
-        )
-        LOG.warning(msg)
-        parsed_cfg.dataset_prepared_path = DEFAULT_DATASET_PREPARED_PATH
-
-    _ = load_datasets(cfg=parsed_cfg, cli_args=parsed_cli_args)
-    LOG.info(
-        Fore.GREEN
-        + f"Success! Preprocessed data path: `dataset_prepared_path: {parsed_cfg.dataset_prepared_path}`"
-        + Fore.RESET
-    )
-
-
-if __name__ == "__main__":
-    fire.Fire(do_cli)
--- a/src/axolotl/cli/shard.py
+++ b/src/axolotl/cli/shard.py
@@ -1,42 +0,0 @@
-"""
-CLI to shard a trained model into 10GiB chunks
-"""
-import logging
-from pathlib import Path
-
-import fire
-import transformers
-
-from axolotl.cli import load_cfg, print_axolotl_text_art
-from axolotl.common.cli import TrainerCliArgs, load_model_and_tokenizer
-from axolotl.utils.dict import DictDefault
-
-LOG = logging.getLogger("axolotl.scripts")
-
-
-def shard(
-    *,
-    cfg: DictDefault,
-    cli_args: TrainerCliArgs,
-):
-    model, _ = load_model_and_tokenizer(cfg=cfg, cli_args=cli_args)
-    safe_serialization = cfg.save_safetensors is True
-    LOG.debug("Re-saving model w/ sharding")
-    model.save_pretrained(cfg.output_dir, safe_serialization=safe_serialization)
-
-
-def do_cli(config: Path = Path("examples/"), **kwargs):
-    # pylint: disable=duplicate-code
-    print_axolotl_text_art()
-    parsed_cfg = load_cfg(config, **kwargs)
-    parser = transformers.HfArgumentParser((TrainerCliArgs))
-    parsed_cli_args, _ = parser.parse_args_into_dataclasses(
-        return_remaining_strings=True
-    )
-    parsed_cli_args.shard = True
-
-    shard(cfg=parsed_cfg, cli_args=parsed_cli_args)
-
-
-if __name__ == "__main__":
-    fire.Fire(do_cli)
--- a/Show More
+++ b/Show More
				`@@ -1 +0,0 @@`
				`See [docs/debugging.md](../docs/debugging.md) for guidance on how to modify these files to debug axolotl with VSCode.`
				`@@ -1 +0,0 @@`
				`This directory contains example config files that might be useful for debugging. Please see [docs/debugging.md](../docs/debugging.md) for more information.`