dataloader defaults

* More correct MoE

* Fix formatting

.bandit

@@ -0,0 +1,3 @@
+[bandit]
+exclude = tests
+skips = B101

.flake8

@@ -0,0 +1,5 @@
+[flake8]
+max-line-length = 88
+
+select = C,E,F,W,B,B950
+extend-ignore = E203, E501, W503

.github/CODE_OF_CONDUCT.md

@@ -0,0 +1,129 @@
+# 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.

.github/CONTRIBUTING.md

@@ -0,0 +1,76 @@
+# 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!

.github/FUNDING.yml

@@ -0,0 +1,13 @@
+# These are supported funding model platforms
+
+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: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+otechie: # Replace with a single Otechie username
+lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
+custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

.github/ISSUE_TEMPLATE/bug-report.yaml

@@ -0,0 +1,112 @@
+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

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,7 @@
+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

.github/ISSUE_TEMPLATE/docs.yml

@@ -0,0 +1,46 @@
+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

.github/ISSUE_TEMPLATE/feature-request.yaml

@@ -0,0 +1,63 @@
+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

.github/PULL_REQUEST_TEMPLATE/pull_request_template_simple.md

@@ -0,0 +1,22 @@
+<!--- 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: -->

.github/SECURITY.md

@@ -0,0 +1,9 @@
+# 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.

.github/SUPPORT.md

@@ -0,0 +1,10 @@
+# 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.

.github/release-drafter.yml

@@ -0,0 +1,31 @@
+name-template: 'v$RESOLVED_VERSION'
+tag-template: 'v$RESOLVED_VERSION'
+categories:
+  - title: '🚀 Features'
+    labels:
+      - 'feature'
+      - 'enhancement'
+  - title: '🐛 Bug Fixes'
+    labels:
+      - 'fix'
+      - 'bugfix'
+      - 'bug'
+  - title: '🧰 Maintenance'
+    label: 'chore'
+change-template: '- $TITLE @$AUTHOR (#$NUMBER)'
+change-title-escapes: '\<*_&' # You can add # and @ to disable mentions, and add ` to disable code blocks.
+version-resolver:
+  major:
+    labels:
+      - 'major'
+  minor:
+    labels:
+      - 'minor'
+  patch:
+    labels:
+      - 'patch'
+  default: patch
+template: |
+  ## What’s Changed
+
+  $CHANGES

.github/workflows/base.yml

@@ -0,0 +1,61 @@
+name: ci-cd-base
+
+on:
+  push:
+    branches:
+      - "main-base"
+      - "dev-base"
+
+jobs:
+  build-base:
+    if: github.repository_owner == 'OpenAccess-AI-Collective'
+    # this job needs to be run on self-hosted GPU runners...
+    runs-on: self-hosted
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - cuda: "118"
+            cuda_version: 11.8.0
+            python_version: "3.9"
+            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: 2.0.1
+            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: 2.1.0
+            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 9.0+PTX"
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+      - name: Docker metadata
+        id: metadata
+        uses: docker/metadata-action@v3
+        with:
+          images: winglian/axolotl-base
+      - name: Login to Docker Hub
+        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@v4
+        with:
+          context: .
+          file: ./docker/Dockerfile-base
+          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 }}
+          labels: ${{ steps.metadata.outputs.labels }}
+          build-args: |
+            CUDA_VERSION=${{ matrix.cuda_version }}
+            CUDA=${{ matrix.cuda }}
+            PYTHON_VERSION=${{ matrix.python_version }}
+            PYTORCH_VERSION=${{ matrix.pytorch }}
+            TORCH_CUDA_ARCH_LIST=${{ matrix.torch_cuda_arch_list }}

.github/workflows/main.yml

@@ -0,0 +1,113 @@
+name: ci-cd
+
+on:
+  push:
+    branches:
+      - "main"
+
+jobs:
+  build-axolotl:
+    if: github.repository_owner == 'OpenAccess-AI-Collective'
+    # this job needs to be run on self-hosted GPU runners...
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - cuda: 118
+            cuda_version: 11.8.0
+            python_version: "3.9"
+            pytorch: 2.0.1
+            axolotl_extras:
+          - cuda: 118
+            cuda_version: 11.8.0
+            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: 2.1.0
+            axolotl_extras:
+    runs-on: [self-hosted, gpu, docker]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+      - name: Docker metadata
+        id: metadata
+        uses: docker/metadata-action@v3
+        with:
+          images: winglian/axolotl
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+      - name: Build
+        uses: docker/build-push-action@v4
+        with:
+          context: .
+          build-args: |
+            BASE_TAG=${{ github.ref_name }}-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}
+            CUDA=${{ matrix.cuda }}
+            PYTORCH_VERSION=${{ matrix.pytorch }}
+          file: ./docker/Dockerfile
+          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) || '' }}
+          labels: ${{ steps.metadata.outputs.labels }}
+  build-axolotl-runpod:
+    needs: build-axolotl
+    if: github.repository_owner == 'OpenAccess-AI-Collective'
+    # this job needs to be run on self-hosted GPU runners...
+    strategy:
+      matrix:
+        include:
+          - cuda: 118
+            cuda_version: 11.8.0
+            python_version: "3.9"
+            pytorch: 2.0.1
+            axolotl_extras:
+          - cuda: 118
+            cuda_version: 11.8.0
+            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: 2.1.0
+            axolotl_extras:
+    runs-on: [self-hosted, gpu, docker]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+      - name: Docker metadata
+        id: metadata
+        uses: docker/metadata-action@v3
+        with:
+          images: winglian/axolotl-runpod
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+      - name: Build
+        uses: docker/build-push-action@v4
+        with:
+          context: .
+          build-args: |
+            BASE_TAG=${{ github.ref_name }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+            CUDA=${{ matrix.cuda }}
+          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) || '' }}
+          labels: ${{ steps.metadata.outputs.labels }}

.github/workflows/pypi.yml

@@ -0,0 +1,45 @@
+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

.github/workflows/tests.yml

@@ -0,0 +1,81 @@
+name: Tests
+on:
+  # check on push/merge to main, PRs, and manual triggers
+  push:
+    branches:
+      - "main"
+    paths:
+      - '**.py'
+      - 'requirements.txt'
+  pull_request:
+      paths:
+       - '**.py'
+       - 'requirements.txt'
+  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
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python_version: ["3.9", "3.10"]
+    timeout-minutes: 10
+
+    steps:
+      - name: Check out repository code
+        uses: actions/checkout@v3
+
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python_version }}
+          cache: 'pip' # caching pip dependencies
+
+      - name: Install dependencies
+        run: |
+          pip3 install -U -e .
+          pip3 install -r requirements-tests.txt
+
+      - name: Run tests
+        run: |
+          pytest --ignore=tests/e2e/ tests/
+
+  e2e-test:
+    name: E2E Tests
+    runs-on: [self-hosted, gpu]
+    timeout-minutes: 20
+    needs: [pre-commit, pytest]
+
+    steps:
+      - name: Check out repository code
+        uses: actions/checkout@v3
+
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+#          cache: 'pip' # caching pip dependencies
+
+      - name: Install dependencies
+        run: |
+          pip3 install --extra-index-url https://download.pytorch.org/whl/cu118 -U torch==2.0.1
+          pip3 uninstall -y transformers accelerate
+          pip3 install -U -e .[flash-attn,mamba-ssm]
+          pip3 install -r requirements-tests.txt
+
+      - name: Run e2e tests
+        run: |
+          pytest tests/e2e/

.gitignore

@@ -1,3 +1,167 @@
 **/axolotl.egg-info
-**/__pycache__
-.idea
+configs
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  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

.isort.cfg

@@ -0,0 +1,3 @@
+[settings]
+profile=black
+known_third_party=wandb

.mypy.ini

@@ -0,0 +1,48 @@
+[mypy]
+
+exclude = venv
+
+[mypy-alpaca_lora_4bit.*]
+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
+
+[mypy-huggingface_hub]
+ignore_missing_imports = True
+
+[mypy-transformers.*]
+ignore_missing_imports = True
+
+[mypy-peft]
+ignore_missing_imports = True
+
+[mypy-wandb]
+ignore_missing_imports = True
+
+[mypy-bitsandbytes]
+ignore_missing_imports = True
+
+[mypy-datasets]
+ignore_missing_imports = True
+
+[mypy-fire]
+ignore_missing_imports = True
+
+[mypy-setuptools]
+ignore_missing_imports = True
+
+[mypy-addict]
+ignore_missing_imports = True
+
+[mypy-xformers.*]
+ignore_missing_imports = True

.pre-commit-config.yaml

@@ -0,0 +1,42 @@
+default_language_version:
+    python: python3
+
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+    -   id: check-yaml
+    -   id: end-of-file-fixer
+    -   id: trailing-whitespace
+-   repo: https://github.com/psf/black
+    rev: 23.3.0
+    hooks:
+    -   id: black
+-   repo: https://github.com/pycqa/isort
+    rev: 5.12.0
+    hooks:
+      - id: isort
+-   repo: https://github.com/PyCQA/flake8
+    rev: 6.0.0
+    hooks:
+    - id: flake8
+-   repo: https://github.com/PyCQA/pylint
+    rev: v2.17.4
+    hooks:
+    - id: pylint
+-   repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.3.0
+    hooks:
+    - id: mypy
+      additional_dependencies:
+        [
+            'types-PyYAML',
+        ]
+-   repo: https://github.com/PyCQA/bandit
+    rev: 1.7.5
+    hooks:
+    -   id: bandit
+        args: [
+            '--ini',
+            '.bandit',
+        ]

.pylintrc

@@ -0,0 +1,14 @@
+[MASTER]
+init-hook="from pylint.config import find_pylintrc; import os, sys; sys.path.append(os.path.dirname(find_pylintrc()))"
+
+[TYPECHECK]
+
+# List of members which are set dynamically and missed by Pylint inference
+# system, and so shouldn't trigger E1101 when accessed.
+generated-members=numpy.*, torch.*
+
+
+[pylint.messages_control]
+disable=missing-function-docstring, line-too-long, import-error,
+    too-many-arguments, too-many-locals, too-many-statements, too-many-branches, too-few-public-methods,
+    too-many-instance-attributes, fixme, import-outside-toplevel, logging-fstring-interpolation,

FAQS.md

@@ -0,0 +1,7 @@
+# FAQs
+
+- Can you train StableLM with this? Yes, but only with a single GPU atm. Multi GPU support is coming soon! Just waiting on this [PR](https://github.com/huggingface/transformers/pull/22874)
+- Will this work with Deepspeed? That's still a WIP, but setting `export ACCELERATE_USE_DEEPSPEED=true` should work in some cases
+- `Error invalid argument at line 359 in file /workspace/bitsandbytes/csrc/pythonInterface.c`
+`/arrow/cpp/src/arrow/filesystem/s3fs.cc:2598:  arrow::fs::FinalizeS3 was not called even though S3 was initialized.`
+This could lead to a segmentation fault at exit. Try reinstalling bitsandbytes and transformers from source.

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

TODO.md

@@ -0,0 +1,10 @@
+# todo list
+
+- [] Validation of parameters for combinations that won't work
+
+
+
+## things that are known not to work
+
+- FSDP offload and gradient_checkpointing - https://github.com/pytorch/pytorch/issues/82203
+- adamw_bnb_8bit doesn't play well with FSDP offload

configs/cerebras_1_3B_alpaca.yml

@@ -1,40 +0,0 @@
-base_model: cerebras/Cerebras-GPT-1.3B
-model_type: AutoModelForCausalLM
-tokenizer_type: AutoTokenizer
-load_in_8bit: true
-datasets:
-  - path: data/alpaca_data_gpt4.jsonl
-    type: alpaca
-  - path: data/vicuna_cleaned.jsonl
-    type: sharegpt
-  - path: data/gpt4-instruct-similarity-0.6-dataset.jsonl
-    type: gpteacher
-  - path: data/roleplay-similarity_0.6-instruct-dataset.jsonl
-    type: gpteacher
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.05
-adapter: lora
-sequence_len: 2048
-lora_r: 8
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-  - c_attn
-lora_fan_in_fan_out: false
-wandb_project: pythia-1.4b-lora
-wandb_watch:
-wandb_run_id:
-wandb_log_model: checkpoint
-output_dir: ./lora-alpaca
-batch_size: 32
-micro_batch_size: 4
-num_epochs: 5
-learning_rate: 0.0003
-train_on_inputs: false
-group_by_length: false
-bf16: True
-tf32: True
-gradient_checkpointing:
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:

configs/llama_65B_alpaca.yml

@@ -1,41 +0,0 @@
-base_model: huggyllama/llama-65b
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-load_in_8bit: true
-datasets:
-  - path: data/alpaca_data_gpt4.jsonl
-    type: alpaca
-  - path: data/vicuna_cleaned.jsonl
-    type: sharegpt
-  - path: data/gpt4-instruct-similarity-0.6-dataset.jsonl
-    type: gpteacher
-  - path: data/roleplay-similarity_0.6-instruct-dataset.jsonl
-    type: gpteacher
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.04
-adapter: lora
-lora_model_dir:
-sequence_len: 2048
-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-65b-lora
-wandb_watch:
-wandb_run_id:
-wandb_log_model: checkpoint
-output_dir: ./lora-llama-alpaca
-batch_size: 128
-micro_batch_size: 16
-num_epochs: 5
-learning_rate: 0.00003
-train_on_inputs: false
-group_by_length: false
-bf16: true
-tf32: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:

configs/llama_7B_4bit.yml

@@ -1,41 +0,0 @@
-base_model: decapoda-research/llama-7b-hf-int4
-base_model_config: decapoda-research/llama-7b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-load_in_8bit: true
-datasets:
-  - path: vicgalle/alpaca-gpt4
-    type: alpaca
-dataset_prepared_path: data/last_run_prepared
-val_set_size: 0.04
-adapter: lora
-lora_model_dir:
-sequence_len: 2048
-max_packed_sequence_len: 1024
-lora_r: 8
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-  - q_proj
-  - v_proj
-#  - k_proj
-#  - o_proj
-lora_fan_in_fan_out: false
-wandb_project:
-wandb_watch:
-wandb_run_id:
-wandb_log_model: checkpoint
-output_dir: ./lora-test
-batch_size: 8
-micro_batch_size: 2
-num_epochs: 3
-learning_rate: 0.00003
-train_on_inputs: false
-group_by_length: false
-bf16: true
-tf32: true
-gradient_checkpointing: false
-early_stopping_patience: 3
-resume_from_checkpoint:
-local_rank:
-load_4bit: true

configs/llama_7B_alpaca.yml

@@ -1,41 +0,0 @@
-base_model: huggyllama/llama-7b
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-load_in_8bit: true
-datasets:
-  - path: data/alpaca_data_gpt4.jsonl
-    type: alpaca
-  - path: data/vicuna_cleaned.jsonl
-    type: sharegpt
-  - path: data/gpt4-instruct-similarity-0.6-dataset.jsonl
-    type: gpteacher
-  - path: data/roleplay-similarity_0.6-instruct-dataset.jsonl
-    type: gpteacher
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.04
-adapter: lora
-lora_model_dir:
-sequence_len: 2048
-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
-wandb_watch:
-wandb_run_id:
-wandb_log_model: checkpoint
-output_dir: ./lora-llama-alpaca
-batch_size: 128
-micro_batch_size: 16
-num_epochs: 5
-learning_rate: 0.00003
-train_on_inputs: false
-group_by_length: false
-bf16: true
-tf32: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:

configs/pythia_1_2B_alpaca.yml

@@ -1,41 +0,0 @@
-base_model: EleutherAI/pythia-1.4b-deduped
-model_type: GPTNeoXForCausalLM
-tokenizer_type: AutoTokenizer
-load_in_8bit: true
-datasets:
-  - path: data/alpaca_data_gpt4.jsonl
-    type: alpaca
-  - path: data/vicuna_cleaned.jsonl
-    type: sharegpt
-  - path: data/gpt4-instruct-similarity-0.6-dataset.jsonl
-    type: gpteacher
-  - path: data/roleplay-similarity_0.6-instruct-dataset.jsonl
-    type: gpteacher
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.05
-adapter: lora
-lora_model_dir:
-sequence_len: 2048
-lora_r: 8
-lora_alpha: 32
-lora_dropout: 0.05
-lora_target_modules:
-  - query_key_value
-#  - xxx
-lora_fan_in_fan_out: true  # pythia/GPTNeoX lora specific
-wandb_project: pythia-1.4b-lora
-wandb_watch:
-wandb_run_id:
-wandb_log_model: checkpoint
-output_dir: ./lora-alpaca
-batch_size: 48
-micro_batch_size: 4
-num_epochs: 5
-learning_rate: 0.00001
-train_on_inputs: false
-group_by_length: false
-bf16: True
-tf32: True
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:

configs/vicuna_13B_4bit_reflect.yml

@@ -1,45 +0,0 @@
-base_model: anon8231489123/vicuna-13b-GPTQ-4bit-128g
-base_model_config: anon8231489123/vicuna-13b-GPTQ-4bit-128g
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-load_in_8bit: false
-load_4bit: true
-gptq_groupsize: 128
-gptq_model_v1: false
-datasets:
-# https://github.com/vaguenebula/AlpacaDataReflect/blob/main/alpaca_reflect_pruned.json
-  - path: data/alpaca_reflect_pruned.jsonl
-    type: reflection
-dataset_prepared_path: data/last_run_prepared
-val_set_size: 0.04
-adapter: lora
-lora_model_dir:
-sequence_len: 2048
-max_packed_sequence_len: 2048
-lora_r: 8
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-  - q_proj
-  - v_proj
-#  - k_proj
-#  - o_proj
-lora_fan_in_fan_out: false
-wandb_project:
-wandb_watch:
-wandb_run_id:
-wandb_log_model: checkpoint
-output_dir: ./lora-reflect
-batch_size: 8
-micro_batch_size: 2
-num_epochs: 3
-learning_rate: 0.00003
-train_on_inputs: false
-group_by_length: false
-bf16: true
-tf32: true
-gradient_checkpointing: false
-early_stopping_patience: 3
-resume_from_checkpoint:
-local_rank:
-flash_attention: true

data/README.md

@@ -1,24 +0,0 @@
-
-- 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 --input data/alpaca_data_gpt4.json > data/alpaca_data_gpt4.jsonl
-python3 ./scripts/alpaca_json_to_jsonl.py --input data/raw/vicuna_cleaned.json > data/vicuna_cleaned.jsonl
-python3 ./scripts/alpaca_json_to_jsonl.py --input data/raw/roleplay-similarity_0.6-instruct-dataset.json > data/roleplay-similarity_0.6-instruct-dataset.jsonl
-python3 ./scripts/alpaca_json_to_jsonl.py --input data/raw/gpt4-instruct-similarity-0.6-dataset.json > 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
-```

data/raw/.gitignore

@@ -1 +0,0 @@
-**

deepspeed/zero1.json

@@ -0,0 +1,31 @@
+{
+  "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
+}

deepspeed/zero2.json

@@ -0,0 +1,35 @@
+{
+  "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
+}

deepspeed/zero3.json

@@ -0,0 +1,39 @@
+{
+  "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": "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
+}

docker-compose.yaml

@@ -0,0 +1,25 @@
+# version: '3.8'
+services:
+  axolotl:
+    build:
+      context: .
+      dockerfile: ./docker/Dockerfile
+    volumes:
+      - .:/workspace/axolotl
+      - ~/.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:
+        reservations:
+          devices:
+            - driver: nvidia
+              # count: 1
+              capabilities: [gpu]
+    command: tail -f /dev/null

docker/Dockerfile

@@ -0,0 +1,34 @@
+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"
+
+ENV PYTORCH_VERSION=$PYTORCH_VERSION
+
+RUN apt-get update && \
+    apt-get install -y vim curl
+
+WORKDIR /workspace
+
+RUN git clone --depth=1 https://github.com/OpenAccess-AI-Collective/axolotl.git
+
+WORKDIR /workspace/axolotl
+
+# If AXOLOTL_EXTRAS is set, append it in brackets
+RUN sed -i "s/torch==.*/torch==$PYTORCH_VERSION/" requirements.txt
+RUN if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
+        pip install -e .[deepspeed,flash-attn,$AXOLOTL_EXTRAS]; \
+    else \
+        pip install -e .[deepspeed,flash-attn]; \
+    fi
+
+# 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

docker/Dockerfile-base

@@ -0,0 +1,37 @@
+ARG CUDA_VERSION="11.8.0"
+ARG CUDNN_VERSION="8"
+ARG UBUNTU_VERSION="22.04"
+ARG MAX_JOBS=4
+
+FROM nvidia/cuda:$CUDA_VERSION-cudnn$CUDNN_VERSION-devel-ubuntu$UBUNTU_VERSION as base-builder
+
+ENV PATH="/root/miniconda3/bin:${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 \
+    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}"
+
+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
+
+RUN git lfs install --skip-repo && \
+    pip3 install awscli && \
+    # The base image ships with `pydantic==1.8.2` which is not working
+    pip3 install -U --no-cache-dir pydantic==1.10.10

docker/Dockerfile-runpod

@@ -0,0 +1,19 @@
+ARG BASE_TAG=main
+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"
+
+COPY scripts/runpod-entrypoint.sh /root/runpod-entrypoint.sh
+
+RUN apt install --yes --no-install-recommends openssh-server tmux && \
+    mkdir -p ~/.ssh && \
+    chmod 700 ~/.ssh && \
+    printf "\n[[ -z \"\$TMUX\"  ]] && { tmux attach-session -t ssh_tmux || tmux new-session -s ssh_tmux; exit; }\n" >> ~/.bashrc && \
+    chmod +x /workspace/axolotl/scripts/runpod-entrypoint.sh && \
+    chmod +x /root/runpod-entrypoint.sh
+
+ENTRYPOINT ["/root/runpod-entrypoint.sh"]
+CMD ["sleep", "infinity"]

docs/faq.md

@@ -0,0 +1,18 @@
+# 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.

docs/multi-node.md

@@ -0,0 +1,45 @@
+# 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.

docs/multipack.md

@@ -0,0 +1,51 @@
+# 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 ]]
+```

docs/nccl.md

@@ -0,0 +1,46 @@
+# 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.

ds_config.json

@@ -1,37 +0,0 @@
-{
-  "bf16": {
-    "enabled": "auto"
-  },
-  "fp16": {
-    "enabled": "auto",
-    "loss_scale": 0,
-    "loss_scale_window": 1000,
-    "initial_scale_power": 16,
-    "hysteresis": 2,
-    "min_loss_scale": 1
-  },
-  "scheduler": {
-    "type": "WarmupLR",
-    "params": {
-      "warmup_min_lr": "auto",
-      "warmup_max_lr": "auto",
-      "warmup_num_steps": "auto"
-    }
-  },
-  "zero_optimization": {
-    "stage": 2,
-    "overlap_comm": true,
-    "allgather_partitions": true,
-    "allgather_bucket_size": 5e8,
-    "contiguous_gradients": true,
-    "reduce_bucket_size": "auto",
-    "reduce_scatter": true
-  },
-  "gradient_accumulation_steps": "auto",
-  "gradient_clipping": "auto",
-  "steps_per_print": 5,
-  "train_batch_size": "auto",
-  "train_micro_batch_size_per_gpu": "auto",
-  "wall_clock_breakdown": false,
-  "round_robin_gradients": true
-}

examples/cerebras/btlm-ft.yml

@@ -0,0 +1,89 @@
+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
+eval_steps:
+save_steps:
+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

examples/cerebras/qlora.yml

@@ -0,0 +1,60 @@
+base_model: cerebras/Cerebras-GPT-1.3B
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+push_dataset_to_hub:
+datasets:
+  - path: teknium/GPT4-LLM-Cleaned
+    type: alpaca
+dataset_prepared_path:
+val_set_size: 0.05
+adapter: qlora
+lora_model_dir:
+sequence_len: 2048
+max_packed_sequence_len: 2048
+lora_r: 16
+lora_alpha: 32
+lora_dropout: 0.05
+lora_target_modules:
+  - c_fc
+  - c_attn
+  - c_proj
+lora_target_linear:
+lora_fan_in_fan_out:
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+output_dir: ./qlora-out
+batch_size: 4
+micro_batch_size: 4
+num_epochs: 2
+optimizer: paged_adamw_8bit
+torchdistx_path:
+lr_scheduler: cosine
+learning_rate: 0.0002
+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: true
+flash_attention:
+gptq_groupsize:
+gptq_model_v1:
+warmup_steps: 10
+eval_steps: 0.05
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.1
+fsdp:
+fsdp_config:
+special_tokens:
+  pad_token: "<|endoftext|>"

examples/code-llama/13b/lora.yml

@@ -0,0 +1,67 @@
+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
+eval_steps: 0.05
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/code-llama/13b/qlora.yml

@@ -0,0 +1,69 @@
+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
+eval_steps: 0.05
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/code-llama/34b/lora.yml

@@ -0,0 +1,67 @@
+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
+eval_steps: 0.05
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/code-llama/34b/qlora.yml

@@ -0,0 +1,69 @@
+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
+eval_steps: 0.05
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/code-llama/7b/lora.yml

@@ -0,0 +1,67 @@
+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
+eval_steps: 0.05
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/code-llama/7b/qlora.yml

@@ -0,0 +1,69 @@
+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
+eval_steps: 0.05
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/code-llama/README.md

@@ -0,0 +1,22 @@
+# 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
+
+```

examples/falcon/config-7b-lora.yml

@@ -0,0 +1,64 @@
+base_model: 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
+strict: false
+push_dataset_to_hub:
+datasets:
+  - path: teknium/GPT4-LLM-Cleaned
+    type: alpaca:chat
+dataset_prepared_path:
+val_set_size: 0.05
+adapter: lora
+lora_model_dir:
+sequence_len: 2048
+max_packed_sequence_len:
+lora_r: 16
+lora_alpha: 32
+lora_dropout: 0.0
+lora_target_modules:
+lora_target_linear: true
+lora_fan_in_fan_out:
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+output_dir: ./falcon-7b
+batch_size: 2
+micro_batch_size: 1
+num_epochs: 4
+optimizer: adamw_bnb_8bit
+torchdistx_path:
+lr_scheduler: cosine
+learning_rate: 0.00003
+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: true
+flash_attention:
+gptq_groupsize:
+gptq_model_v1:
+warmup_steps: 40
+eval_steps: 5
+save_steps: 43
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  pad_token: "<|endoftext|>"
+  bos_token: ">>ABSTRACT<<"
+  eos_token: "<|endoftext|>"

examples/falcon/config-7b-qlora.yml

@@ -0,0 +1,93 @@
+# 1b: tiiuae/falcon-rw-1b
+# 40b: tiiuae/falcon-40b
+base_model: 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
+gptq: false
+strict: false
+push_dataset_to_hub:
+datasets:
+  - path: QingyiSi/Alpaca-CoT
+    data_files:
+      - Chain-of-Thought/formatted_cot_data/gsm8k_train.json
+    type: "alpaca:chat"
+dataset_prepared_path:
+val_set_size: 0.05
+# enable QLoRA
+adapter: qlora
+lora_model_dir:
+sequence_len: 2048
+max_packed_sequence_len:
+
+# hyperparameters from QLoRA paper Appendix B.2
+# "We find hyperparameters to be largely robust across datasets"
+lora_r: 64
+lora_alpha: 16
+# 0.1 for models up to 13B
+# 0.05 for 33B and 65B models
+lora_dropout: 0.05
+# add LoRA modules on all linear layers of the base model
+lora_target_modules:
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+output_dir: ./qlora-out
+
+# QLoRA paper Table 9
+# - 16 for 7b & 13b
+# - 32 for 33b, 64 for 64b
+# Max size tested on A6000
+# - 7b: 40
+# - 40b: 4
+# decrease if OOM, increase for max VRAM utilization
+micro_batch_size: 1
+gradient_accumulation_steps: 2
+num_epochs: 4
+# Optimizer for QLoRA
+optimizer: paged_adamw_32bit
+torchdistx_path:
+lr_scheduler: cosine
+# QLoRA paper Table 9
+# - 2e-4 for 7b & 13b
+# - 1e-4 for 33b & 64b
+learning_rate: 0.0002
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: true
+gradient_checkpointing: true
+# stop training after this many evaluation losses have increased in a row
+# https://huggingface.co/transformers/v4.2.2/_modules/transformers/trainer_callback.html#EarlyStoppingCallback
+early_stopping_patience: 3
+resume_from_checkpoint:
+auto_resume_from_checkpoints: true
+local_rank:
+logging_steps: 1
+xformers_attention: true
+flash_attention:
+gptq_groupsize:
+gptq_model_v1:
+warmup_steps: 10
+eval_steps: 5
+save_steps: 10
+debug:
+deepspeed:
+weight_decay: 0.000001
+fsdp:
+fsdp_config:
+special_tokens:
+  pad_token: "<|endoftext|>"
+  bos_token: ">>ABSTRACT<<"
+  eos_token: "<|endoftext|>"

examples/falcon/config-7b.yml

@@ -0,0 +1,64 @@
+base_model: 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
+strict: false
+push_dataset_to_hub:
+datasets:
+  - path: teknium/GPT4-LLM-Cleaned
+    type: alpaca:chat
+dataset_prepared_path:
+val_set_size: 0.05
+adapter:
+lora_model_dir:
+sequence_len: 2048
+max_packed_sequence_len:
+lora_r: 64
+lora_alpha: 32
+lora_dropout: 0.0
+lora_target_modules:
+lora_target_linear: true
+lora_fan_in_fan_out:
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+output_dir: ./falcon-7b
+batch_size: 2
+micro_batch_size: 1
+num_epochs: 4
+optimizer: adamw_bnb_8bit
+torchdistx_path:
+lr_scheduler: cosine
+learning_rate: 0.00003
+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: true
+flash_attention:
+gptq_groupsize:
+gptq_model_v1:
+warmup_steps: 40
+eval_steps: 5
+save_steps: 43
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  pad_token: "<|endoftext|>"
+  bos_token: ">>ABSTRACT<<"
+  eos_token: "<|endoftext|>"

examples/gptj/qlora.yml

@@ -0,0 +1,57 @@
+base_model: EleutherAI/gpt-j-6b
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+push_dataset_to_hub:
+datasets:
+  - path: teknium/GPT4-LLM-Cleaned
+    type: alpaca
+dataset_prepared_path:
+val_set_size: 0.05
+adapter: qlora
+lora_model_dir:
+sequence_len: 2048
+max_packed_sequence_len:
+lora_r: 8
+lora_alpha: 32
+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:
+output_dir: ./qlora-out
+gradient_accumulation_steps: 2
+micro_batch_size: 2
+num_epochs: 2
+optimizer: paged_adamw_8bit
+torchdistx_path:
+lr_scheduler: cosine
+learning_rate: 0.0001
+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: true
+flash_attention:
+gptq_groupsize:
+gptq_model_v1:
+warmup_steps: 10
+eval_steps: 0.05
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.1
+fsdp:
+fsdp_config:
+special_tokens:
+  pad_token: "<|endoftext|>"

examples/jeopardy-bot/config.yml

@@ -0,0 +1,55 @@
+base_model: huggyllama/llama-7b
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+load_in_8bit: false
+datasets:
+  - path: openaccess-ai-collective/jeopardy
+    type: jeopardy
+dataset_prepared_path:
+val_set_size: 0.02
+adapter:
+lora_model_dir:
+sequence_len: 512
+max_packed_sequence_len:
+lora_r:
+lora_alpha:
+lora_dropout:
+lora_target_modules:
+lora_fan_in_fan_out: false
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+output_dir: ./jeopardy-bot-7b
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+num_epochs: 4
+optimizer: adamw_bnb_8bit
+torchdistx_path:
+lr_scheduler: cosine
+learning_rate: 0.00003
+train_on_inputs: false
+group_by_length: false
+bf16: true
+tf32: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 5
+xformers_attention: true
+flash_attention:
+gptq_groupsize:
+gptq_model_v1:
+warmup_steps: 20
+eval_steps: 110
+save_steps: 660
+debug:
+deepspeed:
+weight_decay: 0.1
+fsdp:
+fsdp_config:
+tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/llama-2/README.md

@@ -0,0 +1,24 @@
+# Overview
+
+This is an example of a llama-2 configuration for 7b and 13b. The yaml file contains configuration for the 7b variant, but you can just aswell use the same settings for 13b.
+
+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
+
+```shell
+accelerate launch -m axolotl.cli.train examples/llama-2/qlora.yml
+```
+or
+
+```shell
+accelerate launch -m axolotl.cli.train 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
+```

examples/llama-2/fft_optimized.yml

@@ -0,0 +1,72 @@
+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
+eval_steps: 0.05
+eval_table_size:
+save_steps:
+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>"

examples/llama-2/gptq-lora.yml

@@ -0,0 +1,73 @@
+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
+eval_steps:
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.1
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/llama-2/lora.yml

@@ -0,0 +1,69 @@
+base_model: NousResearch/Llama-2-7b-hf
+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
+eval_steps: 0.05
+eval_table_size:
+eval_table_max_new_tokens: 128
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/llama-2/qlora.yml

@@ -0,0 +1,70 @@
+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: 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
+eval_steps: 0.05
+eval_table_size:
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/llama-2/relora.yml

@@ -0,0 +1,73 @@
+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
+eval_steps: 0.05
+save_steps: 50
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/llama-2/tiny-llama.yml

@@ -0,0 +1,68 @@
+base_model: PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T
+
+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
+
+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
+eval_steps: 0.05
+eval_table_size:
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/mamba/config.yml

@@ -0,0 +1,61 @@
+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
+eval_steps:
+eval_table_size:
+eval_table_max_new_tokens: 128
+save_steps:  0.25
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+tokens:
+save_safetensors: False

examples/mistral/README.md

@@ -0,0 +1,12 @@
+**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
+```

examples/mistral/config.yml

@@ -0,0 +1,61 @@
+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
+
+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
+eval_steps: 0.05
+eval_table_size:
+eval_table_max_new_tokens: 128
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/mistral/mixtral.yml

@@ -0,0 +1,79 @@
+base_model: DiscoResearch/mixtral-7b-8expert
+model_type: MixtralForCausalLM
+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
+
+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
+eval_steps:
+eval_table_size:
+eval_table_max_new_tokens: 128
+save_steps:
+debug:
+deepspeed: deepspeed/zero2.json
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:

examples/mistral/qlora.yml

@@ -0,0 +1,81 @@
+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: 0.05
+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
+eval_steps: 0.05
+eval_table_size:
+eval_table_max_new_tokens: 128
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/mpt-7b/README.md

@@ -0,0 +1,6 @@
+# MPT-7B
+
+```shell
+accelerate launch scripts/finetune.py examples/mpt-7b/config.yml
+
+```

examples/mpt-7b/config.yml

@@ -0,0 +1,58 @@
+base_model: 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:
+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: mpt-alpaca-7b
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+output_dir: ./mpt-alpaca-7b
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+num_epochs: 4
+optimizer: adamw_bnb_8bit
+torchdistx_path:
+lr_scheduler: cosine
+learning_rate: 0.0000002
+train_on_inputs: false
+group_by_length: false
+bf16: true
+tf32: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 5
+xformers_attention:
+flash_attention:
+gptq_groupsize:
+gptq_model_v1:
+warmup_steps: 20
+eval_steps: 110
+save_steps: 660
+debug:
+deepspeed:
+weight_decay: 0.0001
+fsdp:
+fsdp_config:
+tokens:
+  pad_token: "<|padding|>"
+  bos_token: "<|endoftext|>"
+  eos_token: "<|endoftext|>"
+  unk_token: "<|endoftext|>"

examples/openllama-3b/README.md

@@ -0,0 +1,16 @@
+# openllama-3b
+
+Basic full tune
+```shell
+accelerate launch scripts/finetune.py examples/openllama-3b/config.yml
+```
+
+LoRA
+```shell
+accelerate launch scripts/finetune.py examples/openllama-3b/lora.yml
+```
+
+QLoRA
+```shell
+accelerate launch scripts/finetune.py examples/openllama-3b/qlora.yml
+```

examples/openllama-3b/config.yml

@@ -0,0 +1,62 @@
+base_model: openlm-research/open_llama_3b_v2
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+push_dataset_to_hub:
+datasets:
+  - path: teknium/GPT4-LLM-Cleaned
+    type: alpaca
+dataset_prepared_path:
+val_set_size: 0.02
+adapter:
+lora_model_dir:
+sequence_len: 1024
+sample_packing: true
+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: ./openllama-out
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+num_epochs: 4
+optimizer: adamw_bnb_8bit
+torchdistx_path:
+lr_scheduler: cosine
+learning_rate: 0.000003
+train_on_inputs: false
+group_by_length: false
+float16: true
+bf16: false
+fp16: false
+tf32: false
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+gptq_groupsize:
+gptq_model_v1:
+warmup_steps: 20
+eval_steps: 0.05
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.1
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/openllama-3b/lora.yml

@@ -0,0 +1,67 @@
+base_model: openlm-research/open_llama_3b_v2
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+load_in_8bit: true
+load_in_4bit: false
+strict: false
+push_dataset_to_hub:
+datasets:
+  - path: teknium/GPT4-LLM-Cleaned
+    type: alpaca
+dataset_prepared_path:
+val_set_size: 0.02
+adapter: lora
+lora_model_dir:
+sequence_len: 1024
+sample_packing: true
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.0
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+lora_fan_in_fan_out:
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+output_dir: ./lora-out
+gradient_accumulation_steps: 1
+micro_batch_size: 2
+num_epochs: 4
+optimizer: adamw_bnb_8bit
+torchdistx_path:
+lr_scheduler: cosine
+learning_rate: 0.0002
+train_on_inputs: false
+group_by_length: false
+bf16: false
+fp16: true
+tf32: false
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+gptq_groupsize:
+gptq_model_v1:
+warmup_steps: 20
+eval_steps: 0.05
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.1
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/openllama-3b/qlora.yml

@@ -0,0 +1,61 @@
+base_model: openlm-research/open_llama_3b_v2
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+push_dataset_to_hub:
+datasets:
+  - path: teknium/GPT4-LLM-Cleaned
+    type: alpaca
+dataset_prepared_path:
+val_set_size: 0.05
+adapter: qlora
+lora_model_dir:
+sequence_len: 1024
+sample_packing: true
+lora_r: 8
+lora_alpha: 32
+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:
+output_dir: ./qlora-out
+gradient_accumulation_steps: 1
+micro_batch_size: 2
+num_epochs: 4
+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
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+gptq_groupsize:
+gptq_model_v1:
+warmup_steps: 20
+eval_steps: 0.05
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.1
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/phi/README.md

@@ -0,0 +1,11 @@
+# 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
+```

examples/phi/phi-ft.yml

@@ -0,0 +1,74 @@
+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
+eval_steps: 0.05
+save_steps:
+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|>"

examples/phi/phi-qlora.yml

@@ -0,0 +1,74 @@
+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
+eval_steps: 0.05
+save_steps:
+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|>"

examples/pythia-12b/README.md

@@ -0,0 +1,9 @@
+# Pythia 12B
+
+- Single-GPU A100 only (?)
+
+```shell
+python scripts/finetune.py examples/pythia-12b/config.yml
+```
+
+⚠️ Multiple-GPU A100 - Doesn't seem to work with multi-gpu without causing OOM! ⚠️

examples/pythia-12b/config.yml

@@ -0,0 +1,48 @@
+base_model: EleutherAI/pythia-12b-deduped
+base_model_ignore_patterns: pytorch*  # prefer safetensors
+model_type: GPTNeoXForCausalLM
+tokenizer_type: AutoTokenizer
+load_in_8bit: false
+load_in_4bit: false
+gptq: false
+device_map: auto
+datasets:
+  - path: vicgalle/alpaca-gpt4
+    type: alpaca
+dataset_prepared_path:
+val_set_size: 0.05
+adapter:
+lora_model_dir:
+sequence_len: 2048
+max_packed_sequence_len: 2048
+lora_r: 64
+lora_alpha: 32
+lora_dropout: 0.0
+lora_target_modules:
+lora_target_linear: true
+lora_fan_in_fan_out: true  # pythia/GPTNeoX lora specific
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+output_dir: ./pythia-12b
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+num_epochs: 5
+learning_rate: 0.00003
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+train_on_inputs: false
+group_by_length: false
+bf16: false
+fp16: false
+float16: true
+tf32: true
+flash_optimum: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+gradient_checkpointing: true
+fsdp:
+fsdp_config:

examples/pythia/lora.yml

@@ -0,0 +1,37 @@
+base_model: EleutherAI/pythia-1.4b-deduped
+load_in_8bit: true
+datasets:
+  - path: teknium/GPT4-LLM-Cleaned
+    type: alpaca
+dataset_prepared_path:
+val_set_size: 0.05
+adapter: lora
+lora_model_dir:
+sequence_len: 512
+lora_r: 16
+lora_alpha: 32
+lora_dropout: 0.05
+lora_target_modules:
+  - query_key_value
+lora_target_linear:
+lora_fan_in_fan_out: true  # pythia/GPTNeoX lora specific
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+output_dir: ./lora-alpaca-pythia
+gradient_accumulation_steps: 1
+micro_batch_size: 4
+num_epochs: 4
+learning_rate: 0.00001
+train_on_inputs: false
+group_by_length: false
+bf16: true
+tf32: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+weight_decay: 0.1
+eval_steps: 0.05
+logging_steps: 1

examples/qwen/lora.yml

@@ -0,0 +1,68 @@
+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
+eval_steps: 0.05
+eval_table_size:
+eval_table_max_new_tokens: 128
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:

examples/qwen/qlora.yml

@@ -0,0 +1,68 @@
+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
+eval_steps: 0.05
+eval_table_size:
+eval_table_max_new_tokens: 128
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:

examples/redpajama/README.md

@@ -0,0 +1,6 @@
+# RedPajama 3B preview release
+
+```shell
+accelerate launch scripts/finetune.py examples/redpajama/config-3b.yml
+
+```

examples/redpajama/config-3b.yml

@@ -0,0 +1,59 @@
+base_model: togethercomputer/RedPajama-INCITE-Chat-3B-v1
+model_type: GPTNeoXForCausalLM
+tokenizer_type: AutoTokenizer
+trust_remote_code:
+load_in_8bit: false
+datasets:
+  - path: vicgalle/alpaca-gpt4
+    type: alpaca
+dataset_prepared_path:
+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: redpajama-alpaca-3b
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+output_dir: ./redpajama-alpaca-3b
+batch_size: 4
+micro_batch_size: 1
+num_epochs: 4
+optimizer: adamw_bnb_8bit
+torchdistx_path:
+lr_scheduler: cosine
+learning_rate: 0.0000002
+train_on_inputs: false
+group_by_length: false
+bf16: true
+tf32: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 5
+xformers_attention:
+flash_attention:
+gptq_groupsize:
+gptq_model_v1:
+warmup_steps: 20
+eval_steps: 110
+save_steps: 660
+debug:
+deepspeed:
+weight_decay: 0.0001
+fsdp:
+fsdp_config:
+tokens:
+  pad_token: "<|padding|>"
+  bos_token: "<|endoftext|>"
+  eos_token: "<|endoftext|>"
+  unk_token: "<|endoftext|>"

examples/replit-3b/config-lora.yml

@@ -0,0 +1,55 @@
+base_model: replit/replit-code-v1-3b
+trust_remote_code: true
+load_in_8bit: false
+datasets:
+  - path: vicgalle/alpaca-gpt4
+    type: alpaca
+dataset_prepared_path:
+val_set_size: 0.05
+adapter: lora
+lora_model_dir:
+sequence_len: 2048
+max_packed_sequence_len:
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+  - Wqkv
+  - mlp_up
+  - mlp_down
+lora_fan_in_fan_out:
+wandb_project: lora-replit
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+output_dir: ./lora-replit
+batch_size: 8
+micro_batch_size: 1
+num_epochs: 4
+optimizer:
+torchdistx_path:
+lr_scheduler:
+learning_rate: 0.00001
+train_on_inputs: false
+group_by_length: false
+bf16: true
+tf32: true
+gradient_checkpointing:
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention:
+gptq_groupsize:
+gptq_model_v1:
+warmup_steps: 20
+eval_steps: 50
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0
+fsdp:
+fsdp_config:
+#special_tokens:

examples/xgen-7b/xgen-7b-8k-qlora.yml

@@ -0,0 +1,90 @@
+# 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
+trust_remote_code: true
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+load_in_8bit: false
+# enable 4bit for QLoRA
+load_in_4bit: true
+gptq: false
+strict: false
+push_dataset_to_hub:
+datasets:
+  - path: timdettmers/openassistant-guanaco
+    data_files:
+      - openassistant_best_replies_train.jsonl
+    type: "completion"
+dataset_prepared_path:
+val_set_size: 0.05
+# enable QLoRA
+adapter: qlora
+lora_model_dir:
+sequence_len: 8192
+max_packed_sequence_len:
+
+# hyperparameters from QLoRA paper Appendix B.2
+# "We find hyperparameters to be largely robust across datasets"
+lora_r: 64
+lora_alpha: 16
+# 0.1 for models up to 13B
+# 0.05 for 33B and 65B models
+lora_dropout: 0.05
+# add LoRA modules on all linear layers of the base model
+lora_target_modules:
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+output_dir: ./qlora-out
+
+# QLoRA paper Table 9
+# - 16 for 7b & 13b
+# - 32 for 33b, 64 for 64b
+# Max size tested on A6000
+# - 7b: 40
+# - 40b: 4
+# decrease if OOM, increase for max VRAM utilization
+micro_batch_size: 1
+gradient_accumulation_steps: 1
+num_epochs: 4
+# Optimizer for QLoRA
+optimizer: paged_adamw_32bit
+torchdistx_path:
+lr_scheduler: cosine
+# QLoRA paper Table 9
+# - 2e-4 for 7b & 13b
+# - 1e-4 for 33b & 64b
+learning_rate: 0.00002
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+gradient_checkpointing: true
+# stop training after this many evaluation losses have increased in a row
+# https://huggingface.co/transformers/v4.2.2/_modules/transformers/trainer_callback.html#EarlyStoppingCallback
+early_stopping_patience: 3
+resume_from_checkpoint:
+auto_resume_from_checkpoints: true
+local_rank:
+logging_steps: 1
+xformers_attention: true
+flash_attention:
+gptq_groupsize:
+gptq_model_v1:
+warmup_steps: 10
+eval_steps: 50
+save_steps: 50
+debug:
+deepspeed:
+weight_decay: 0.0
+special_tokens:
+  eos_token: "<|endoftext|>"
+  bos_token: "<|endoftext|>"
+  unk_token: "<|endoftext|>"
+  pad_token: "<|endoftext|>"

requirements-dev.txt

@@ -0,0 +1,3 @@
+pre-commit
+black
+mypy

requirements-tests.txt

@@ -0,0 +1 @@
+pytest

requirements.txt

@@ -1,14 +1,39 @@
-peft @ git+https://github.com/huggingface/peft.git
-transformers @ git+https://github.com/huggingface/transformers.git
-attrdict
+--extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
+auto-gptq==0.5.1
+packaging
+peft==0.6.0
+transformers @ git+https://github.com/huggingface/transformers.git@df5c5c62ae253055336f5bb0828ca8e3e15ab6bd
+tokenizers==0.15.0
+bitsandbytes>=0.41.1
+accelerate==0.24.1
+deepspeed
+addict
 fire
-PyYAML==6.0
-black
-bitsandbytes
-datasets
-accelerate
+PyYAML>=6.0
+datasets>=2.15.0
+flash-attn==2.3.3
 sentencepiece
 wandb
-flash-attn
-deepspeed
 einops
+xformers==0.0.22
+optimum==1.13.2
+hf_transfer
+colorama
+numba
+numpy>=1.24.4
+# qlora things
+bert-score==0.3.13
+evaluate==0.4.0
+rouge-score==0.1.2
+scipy
+scikit-learn==1.2.2
+pynvml
+art
+fschat==0.2.29
+gradio==3.50.2
+tensorboard
+
+# remote filesystems
+s3fs
+gcsfs
+# adlfs

scripts/alpaca_json_to_jsonl.py

@@ -1,35 +0,0 @@
-import os
-import sys
-from pathlib import Path
-
-import fire
-from typing import Optional
-
-# 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)
-
-from axolotl.convert import *
-
-
-def main(
-    input: Path,
-    output: Optional[Path] = None,
-    to_stdout: Optional[bool] = False,
-):
-    file_reader = FileReader()
-    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(input, output)
-
-
-if __name__ == "__main__":
-    fire.Fire(main)

scripts/finetune.py

@@ -1,619 +1,52 @@
+"""Prepare and train a model on a dataset. Can also infer from a model or merge lora"""
 import logging
-import math
-import os
-import random
-import signal
-import sys
-from hashlib import md5
 from pathlib import Path
 
-import bitsandbytes as bnb
 import fire
-import torch
 import transformers
-import yaml
-from attrdict import AttrDefault
-from datasets import load_dataset, IterableDataset, Dataset, load_from_disk
-from torch import nn
-from transformers import (
-    AutoModelForCausalLM,
-    AutoTokenizer,
-    LlamaForCausalLM,
-    LlamaTokenizer,
-    EarlyStoppingCallback,
-    GenerationConfig,
+
+from axolotl.cli import (
+    check_accelerate_default_config,
+    check_user_token,
+    do_inference,
+    do_merge_lora,
+    load_cfg,
+    load_datasets,
+    print_axolotl_text_art,
 )
+from axolotl.cli.shard import shard
+from axolotl.common.cli import TrainerCliArgs
+from axolotl.train import train
 
-# add src to the pythonpath so we don't need to pip install this
-from transformers.trainer_pt_utils import get_parameter_names
-
-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)
-
-from axolotl.datasets import TokenizedPromptDataset, ConstantLengthDataset
-from axolotl.prompt_tokenizers import (
-    AlpacaPromptTokenizingStrategy,
-    ShareGPTPromptTokenizingStrategy,
-    LLAMA_DEFAULT_PAD_TOKEN,
-    GPTeacherPromptTokenizingStrategy,
-    OpenAssistantPromptTokenizingStrategy, AlpacaReflectionPTStrategy,
-)
-from axolotl.prompters import AlpacaPrompter, GPTeacherPrompter, ShareGPTPrompter, ReflectAlpacaPrompter
-
-logging.basicConfig(level=os.getenv("LOG_LEVEL", "INFO"))
-DEFAULT_DATASET_PREPARED_PATH = "last_run_prepared"
+LOG = logging.getLogger("axolotl.scripts.finetune")
 
 
-def setup_wandb_env_vars(cfg):
-    if cfg.wandb_project and len(cfg.wandb_project) > 0:
-        os.environ["WANDB_PROJECT"] = cfg.wandb_project
-        cfg.use_wandb = True
-        if cfg.wandb_watch and len(cfg.wandb_watch) > 0:
-            os.environ["WANDB_WATCH"] = cfg.wandb_watch
-        if cfg.wandb_log_model and len(cfg.wandb_log_model) > 0:
-            os.environ["WANDB_LOG_MODEL"] = cfg.wandb_log_model
-        if cfg.wandb_run_id and len(cfg.wandb_run_id) > 0:
-            os.environ["WANDB_RUN_ID"] = cfg.wandb_run_id
-
-
-def load_model(
-    base_model,
-    base_model_config,
-    model_type,
-    tokenizer_type,
-    cfg,
-    adapter="lora",
-    inference: bool = False,
-):
-    # TODO refactor as a kwarg
-    load_in_8bit = cfg.load_in_8bit
-    tokenizer = None
-    is_llama_derived_model = "llama" in base_model or "llama" in cfg.model_type.lower()
-
-    if adapter != "lora":
-        raise NotImplementedError(f"{adapter} peft adapter not available")
-    if is_llama_derived_model and cfg.flash_attention:
-        if cfg.device not in ["mps", "cpu"] and inference is False:
-            from axolotl.flash_attn import replace_llama_attn_with_flash_attn
-
-            logging.info("patching with flash attention")
-            replace_llama_attn_with_flash_attn()
-
-    torch_dtype = (torch.float16 if cfg.load_in_8bit or cfg.fp16 else torch.float32,)
-    try:
-        if cfg.load_4bit:
-            from alpaca_lora_4bit.monkeypatch.peft_tuners_lora_monkey_patch import (
-                replace_peft_model_with_int4_lora_model,
+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"
             )
-
-            replace_peft_model_with_int4_lora_model()
-
-        from peft import (
-            LoraConfig,
-            get_peft_model,
-            prepare_model_for_int8_training,
-            PeftModel,
         )
-    except Exception as e:
-        logging.exception(e)
-        raise e
-
-    try:
-        if cfg.load_4bit and is_llama_derived_model:
-            from alpaca_lora_4bit.autograd_4bit import load_llama_model_4bit_low_ram
-            from huggingface_hub import snapshot_download
-
-            cache_model_path = Path(snapshot_download(base_model))
-            files = (
-                list(cache_model_path.glob("*.pt"))
-                + list(cache_model_path.glob("*.safetensors"))
-                + list(cache_model_path.glob("*.bin"))
-            )
-            if len(files) > 0:
-                model_path = str(files[0])
-            else:
-                logging.warning(
-                    "unable to find a cached model file, this will likely fail..."
-                )
-                model_path = str(cache_model_path)
-            model, tokenizer = load_llama_model_4bit_low_ram(
-                base_model_config if base_model_config else base_model,
-                model_path,
-                device_map=cfg.device_map,
-                groupsize=cfg.gptq_groupsize if cfg.gptq_groupsize else -1,
-                is_v1_model=cfg.gptq_model_v1
-                if cfg.gptq_model_v1 is not None
-                else True,
-            )
-            load_in_8bit = False
-        elif is_llama_derived_model:
-            model = LlamaForCausalLM.from_pretrained(
-                base_model,
-                load_in_8bit=cfg.load_in_8bit,
-                torch_dtype=torch_dtype,
-                device_map=cfg.device_map,
-            )
-        else:
-            model = getattr(transformers, model_type).from_pretrained(
-                base_model,
-                load_in_8bit=cfg.load_in_8bit,
-                torch_dtype=torch_dtype,
-                device_map=cfg.device_map,
-            )
-    except Exception as e:
-        logging.error(
-            "Exception raised attempting to load model, retrying with AutoModelForCausalLM"
-        )
-        logging.exception(e)
-        model = AutoModelForCausalLM.from_pretrained(
-            base_model,
-            load_in_8bit=cfg.load_in_8bit,
-            torch_dtype=torch_dtype,
-            device_map=cfg.device_map,
-        )
-
-    if not tokenizer:
-        try:
-            if is_llama_derived_model:
-                tokenizer = LlamaTokenizer.from_pretrained(model)
-            else:
-                tokenizer = getattr(transformers, tokenizer_type).from_pretrained(model)
-        except:
-            tokenizer = AutoTokenizer.from_pretrained(base_model)
-
-    logging.debug(f"EOS: {tokenizer.eos_token_id} / {tokenizer.eos_token}")
-    logging.debug(f"BOS: {tokenizer.bos_token_id} / {tokenizer.bos_token}")
-    logging.debug(f"PAD: {tokenizer.pad_token_id} / {tokenizer.pad_token}")
-    logging.debug(f"UNK: {tokenizer.unk_token_id} / {tokenizer.unk_token}")
-
-    if tokenizer.__class__.__name__ in ["LlamaTokenizer", "LlamaTokenizerFast"]:
-        tokenizer.pad_token = LLAMA_DEFAULT_PAD_TOKEN
-
-    if tokenizer.__class__.__name__ == "GPTNeoXTokenizerFast":
-        tokenizer.add_special_tokens({"pad_token": "[PAD]"})
-        os.environ["TOKENIZERS_PARALLELISM"] = "false"
-
-    if load_in_8bit and not cfg.load_4bit:
-        logging.info("converting model w/ prepare_model_for_int8_training")
-        model = prepare_model_for_int8_training(model)
-
-    lora_config = LoraConfig(
-        r=cfg.lora_r,
-        lora_alpha=cfg.lora_alpha,
-        target_modules=cfg.lora_target_modules,
-        lora_dropout=cfg.lora_dropout,
-        fan_in_fan_out=cfg.lora_fan_in_fan_out,
-        bias="none",
-        task_type="CAUSAL_LM",
     )
-
-    if cfg.lora_model_dir:
-        model = PeftModel.from_pretrained(
-            model,
-            cfg.lora_model_dir,
-            device_map=cfg.device_map,
-            torch_dtype=torch.float16,
-        )
+    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)
     else:
-        model = get_peft_model(model, lora_config)
-
-    if cfg.ddp:
-        model.to(f"cuda:{cfg.local_rank}")
-
-    if cfg.load_4bit:
-        # Scales to half
-        logging.info("Fitting 4bit scales and zeros to half")
-        for n, m in model.named_modules():
-            if "Autograd4bitQuantLinear" in str(type(m)) or "Linear4bitLt" in str(
-                type(m)
-            ):
-                if hasattr(m, "is_v1_model") and m.is_v1_model:
-                    m.zeros = m.zeros.half()
-                m.scales = m.scales.half()
-                m.bias = m.bias.half()
-
-    # TODO resume_from_checkpoint handling
-    model.print_trainable_parameters()
-    return model, tokenizer, lora_config
-
-
-def choose_device(cfg):
-    def get_device():
-        if torch.cuda.is_available():
-            return "cuda"
-        else:
-            try:
-                if torch.backends.mps.is_available():
-                    return "mps"
-            except:
-                return "cpu"
-
-    cfg.device = get_device()
-    if cfg.device == "cuda":
-        cfg.device_map = {"": cfg.local_rank}
-    else:
-        cfg.device_map = {"": cfg.device}
-
-
-def check_dataset_labels(dataset, tokenizer):
-    from termcolor import colored
-
-    # the dataset is already shuffled, so let's just check the first 5 elements
-    for idx in range(5):
-        # Get the input_ids, labels, and attention_mask from the dataset
-        input_ids = dataset[idx]["input_ids"]
-        labels = dataset[idx]["labels"]
-        attention_mask = dataset[idx]["attention_mask"]
-
-        # You can compare the input_ids and labels element-wise
-        # Remember to ignore positions with IGNORE_TOKEN_ID (if you use it) or attention_mask equal to 0
-        colored_tokens = []
-        for i, (input_id, label_id, mask) in enumerate(
-            zip(input_ids, labels, attention_mask)
-        ):
-            decoded_input_token = tokenizer.decode(input_id)
-            # Choose the color based on whether the label has the ignore value or not
-            color = (
-                "red" if label_id == -100 else ("yellow" if label_id == 0 else "green")
-            )
-            colored_token = colored(decoded_input_token, color) + colored(
-                f"({label_id}, {mask})", "white"
-            )
-            colored_tokens.append(colored_token)
-
-        logging.info(" ".join(colored_tokens))
-        logging.info("\n\n\n")
-
-
-def do_inference(cfg, model, tokenizer):
-    tokenizer.add_special_tokens({"unk_token": "<unk>"})
-    tokenizer.add_special_tokens({"bos_token": "<s>"})
-    tokenizer.add_special_tokens({"eos_token": "</s>"})
-
-    instruction = "Tell me a joke about dromedaries."
-    input = ""
-    prompt = "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:\n".format(
-        instruction=instruction, input=input
-    )
-    batch = tokenizer(prompt, return_tensors="pt", add_special_tokens=True)
-
-    model.eval()
-    with torch.no_grad():
-        # gc = GenerationConfig()  # TODO swap out and use this
-        generated = model.generate(
-            inputs=batch["input_ids"].to("cuda"),
-            do_sample=True,
-            use_cache=True,
-            repetition_penalty=1.1,
-            max_new_tokens=100,
-            temperature=0.9,
-            top_p=0.95,
-            top_k=40,
-            return_dict_in_generate=True,
-            output_attentions=False,
-            output_hidden_states=False,
-            output_scores=False,
-        )
-    print(tokenizer.decode(generated["sequences"].cpu().tolist()[0]))
-
-
-def choose_config(path: Path):
-    yaml_files = [file for file in 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 setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer):
-    total_num_steps = int(
-        math.ceil(len(train_dataset) * cfg.num_epochs / cfg.batch_size)
-    )
-    warmup_steps = min(int(0.03 * total_num_steps), 100)
-    logging_steps = max(min(int(0.005 * total_num_steps), 10), 1)
-    save_steps = eval_steps = min(int(0.05 * total_num_steps), 200)
-
-    training_arguments_kwargs = {}
-    if cfg.bf16 == "full":
-        training_arguments_kwargs["bf16_full_eval"] = True
-    else:
-        training_arguments_kwargs["bf16"] = cfg.bf16
-    training_arguments_kwargs["tf32"] = cfg.tf32
-    training_arguments_kwargs["warmup_steps"] = warmup_steps
-    training_arguments_kwargs["logging_steps"] = logging_steps
-    if cfg.gradient_checkpointing is not None:
-        training_arguments_kwargs["gradient_checkpointing"] = cfg.gradient_checkpointing
-
-    training_args = transformers.TrainingArguments(
-        per_device_train_batch_size=cfg.micro_batch_size,
-        gradient_accumulation_steps=cfg.gradient_accumulation_steps,
-        num_train_epochs=cfg.num_epochs,
-        learning_rate=cfg.learning_rate,
-        evaluation_strategy="steps" if cfg.val_set_size > 0 else "no",
-        save_strategy="steps",
-        eval_steps=eval_steps if cfg.val_set_size > 0 else None,
-        save_steps=save_steps,
-        output_dir=cfg.output_dir,
-        save_total_limit=3,
-        load_best_model_at_end=True if cfg.val_set_size > 0 else False,
-        ddp_find_unused_parameters=False if cfg.ddp else None,
-        group_by_length=cfg.group_by_length,
-        report_to="wandb" if cfg.use_wandb else None,
-        run_name=cfg.wandb_run_id if cfg.use_wandb else None,
-        **training_arguments_kwargs,
-    )
-
-    decay_parameters = get_parameter_names(model, [nn.LayerNorm])
-    decay_parameters = [name for name in decay_parameters if "bias" not in name]
-    optimizer_grouped_parameters = [
-        {
-            "params": [p for n, p in model.named_parameters() if n in decay_parameters],
-            "weight_decay": training_args.weight_decay,
-        },
-        {
-            "params": [
-                p for n, p in model.named_parameters() if n not in decay_parameters
-            ],
-            "weight_decay": 0.0,
-        },
-    ]
-
-    trainer_kwargs = {}
-
-    if cfg.load_in_8bit and not cfg.load_4bit:
-        adam_bnb_optim = bnb.optim.Adam8bit(
-            optimizer_grouped_parameters,
-            betas=(training_args.adam_beta1, training_args.adam_beta2),
-            eps=training_args.adam_epsilon,
-            lr=training_args.learning_rate,
-        )
-
-        # TODO optionally use torch.optim.OneCycleLR
-        lr_scheduler = transformers.get_cosine_schedule_with_warmup(
-            adam_bnb_optim,
-            training_args.warmup_steps,
-            total_num_steps,
-        )
-        trainer_kwargs["optimizers"] = (adam_bnb_optim, lr_scheduler)
-
-    # TODO on_save callback to sync checkpoints to GCP/AWS in background
-    if cfg.early_stopping_patience:
-        early_stop_cb = EarlyStoppingCallback(
-            cfg.early_stopping_patience,
-        )
-        trainer_kwargs["callbacks"] = [early_stop_cb]
-
-    trainer = transformers.Trainer(
-        model=model,
-        train_dataset=train_dataset,
-        eval_dataset=eval_dataset,
-        args=training_args,
-        data_collator=transformers.DataCollatorForSeq2Seq(
-            tokenizer, pad_to_multiple_of=8, return_tensors="pt", padding=True
-        ),
-        **trainer_kwargs,
-    )
-
-    return trainer
-
-
-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, "r") as f:
-        cfg: AttrDefault = AttrDefault(lambda: None, yaml.load(f, Loader=yaml.Loader))
-    # 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 = dict(cfg).keys()
-    for k in kwargs:
-        if k in cfg_keys:
-            # handle booleans
-            if isinstance(cfg[k], bool):
-                cfg[k] = bool(kwargs[k])
-            else:
-                cfg[k] = kwargs[k]
-
-    # setup some derived config / hyperparams
-    cfg.gradient_accumulation_steps = cfg.batch_size // cfg.micro_batch_size
-    cfg.world_size = int(os.environ.get("WORLD_SIZE", 1))
-    cfg.local_rank = int(os.environ.get("LOCAL_RANK", 0))
-    choose_device(cfg)
-    cfg.ddp = cfg.world_size != 1
-    if cfg.ddp:
-        cfg.device_map = {"": int(os.environ.get("LOCAL_RANK", 0))}
-        cfg.gradient_accumulation_steps = (
-            cfg.gradient_accumulation_steps // cfg.world_size
-        )
-    setup_wandb_env_vars(cfg)
-    if cfg.device == "mps":
-        cfg.load_in_8bit = False
-        cfg.tf32 = False
-        if cfg.bf16:
-            cfg.fp16 = True
-        cfg.bf16 = False
-
-    # Load the model and tokenizer
-    logging.info("loading model, tokenizer, and lora_config...")
-    model, tokenizer, lora_config = load_model(
-        cfg.base_model,
-        cfg.base_model_config,
-        cfg.model_type,
-        cfg.tokenizer_type,
-        cfg,
-        adapter=cfg.adapter,
-        inference=("inference" in kwargs),
-    )
-
-    if "inference" in kwargs:
-        logging.info("calling do_inference function")
-        do_inference(cfg, model, tokenizer)
-        return
-
-    max_packed_sequence_len = (
-        cfg.max_packed_sequence_len if cfg.max_packed_sequence_len else cfg.sequence_len
-    )
-    max_packed_sequence_len = min(
-        max_packed_sequence_len, cfg.sequence_len
-    )  # make sure we don't accidentally set it larger than sequence_len
-    ds_hash = str(
-        md5(
-            (
-                str(max_packed_sequence_len)
-                + "@"
-                + "|".join(sorted([f"{d.path}:{d.type}" for d in cfg.datasets]))
-            ).encode("utf-8")
-        ).hexdigest()
-    )
-    prepared_ds_path = (
-        Path(cfg.dataset_prepared_path) / ds_hash
-        if cfg.dataset_prepared_path
-        else Path(DEFAULT_DATASET_PREPARED_PATH) / ds_hash
-    )
-
-    if any(prepared_ds_path.glob("*")):
-        logging.info("Loading prepared dataset from disk...")
-        dataset = load_from_disk(str(prepared_ds_path))
-        logging.info("Prepared dataset loaded from disk...")
-    else:
-        logging.info("Loading raw datasets...")
-        datasets = []
-        for d in cfg.datasets:
-            ds_from_hub = False
-            try:
-                load_dataset(d.path, streaming=True)
-                ds_from_hub = True
-            except FileNotFoundError:
-                pass
-
-            # prefer local dataset, even if hub exists
-            if Path(d.path).exists():
-                ds: IterableDataset = load_dataset(
-                    "json", data_files=d.path, streaming=True, split=None
-                )
-            elif ds_from_hub:
-                ds = load_dataset(d.path, streaming=True)
-            else:
-                raise Exception("unhandled dataset load")
-
-            if d.type == "alpaca":
-                ds_strategy = AlpacaPromptTokenizingStrategy(
-                    AlpacaPrompter(), tokenizer, cfg.train_on_inputs, cfg.sequence_len
-                )
-                ds_wrapper = TokenizedPromptDataset(ds_strategy, ds["train"])
-                datasets.append(ds_wrapper)
-            elif d.type == "oasst":
-                ds_strategy = OpenAssistantPromptTokenizingStrategy(
-                    AlpacaPrompter(), tokenizer, cfg.train_on_inputs, cfg.sequence_len
-                )
-                ds_wrapper = TokenizedPromptDataset(ds_strategy, ds["train"])
-                datasets.append(ds_wrapper)
-            elif d.type == "gpteacher":
-                ds_strategy = GPTeacherPromptTokenizingStrategy(
-                    GPTeacherPrompter(),
-                    tokenizer,
-                    cfg.train_on_inputs,
-                    cfg.sequence_len,
-                )
-                ds_wrapper = TokenizedPromptDataset(ds_strategy, ds["train"])
-                datasets.append(ds_wrapper)
-            elif d.type == "reflection":
-                ds_strategy = AlpacaReflectionPTStrategy(
-                    ReflectAlpacaPrompter(),
-                    tokenizer,
-                    cfg.train_on_inputs,
-                    cfg.sequence_len,
-                )
-                ds_wrapper = TokenizedPromptDataset(ds_strategy, ds["train"])
-                datasets.append(ds_wrapper)
-            elif d.type == "sharegpt":
-                ds_strategy = ShareGPTPromptTokenizingStrategy(
-                    ShareGPTPrompter(), tokenizer, cfg.train_on_inputs, cfg.sequence_len
-                )
-                ds_wrapper = TokenizedPromptDataset(ds_strategy, ds["train"])
-                datasets.append(ds_wrapper)
-            else:
-                logging.error(f"unhandled prompt tokenization strategy: {d.type}")
-        constant_len_dataset = ConstantLengthDataset(
-            tokenizer,
-            datasets,
-            seq_length=max_packed_sequence_len,
-        )
-        logging.info("merging, packing, shuffling, and splitting master dataset")
-        dataset = Dataset.from_list([_ for _ in constant_len_dataset]).train_test_split(
-            test_size=cfg.val_set_size, shuffle=True, seed=42
-        )
-
-        if cfg.local_rank == 0:
-            logging.info(f"Saving prepared dataset to disk... {prepared_ds_path}")
-            dataset.save_to_disk(prepared_ds_path)
-
-        if prepare_ds_only:
-            logging.info("Finished preparing dataset. Exiting...")
-            return
-
-    train_dataset = dataset["train"]
-    eval_dataset = dataset["test"]
-
-    if cfg.debug:
-        check_dataset_labels(
-            train_dataset.select([random.randrange(0, len(train_dataset) - 1)]),
-            tokenizer,
-        )
-
-    trainer = setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer)
-
-    model.config.use_cache = False
-
-    if torch.__version__ >= "2" and sys.platform != "win32":
-        logging.info("Compiling torch model")
-        model = torch.compile(model)
-
-    # go ahead and presave, so we have the adapter config available to inspect
-    logging.info(f"Pre-saving adapter config to {cfg.output_dir}")
-    lora_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:
-        signal.signal(
-            signal.SIGINT,
-            lambda signal, frame: (model.save_pretrained(cfg.output_dir), exit(0)),
-        )
-
-    logging.info("Starting trainer...")
-    trainer.train(resume_from_checkpoint=cfg.resume_from_checkpoint)
-
-    if cfg.local_rank == 0:
-        # TODO do we need this fix? https://huggingface.co/docs/accelerate/usage_guides/fsdp#saving-and-loading
-        logging.info(
-            f"Training Completed!!! Saving pre-trained model to {cfg.output_dir}"
-        )
-        model.save_pretrained(cfg.output_dir)
+        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)
 
 
 if __name__ == "__main__":
-    fire.Fire(train)
+    fire.Fire(do_cli)

scripts/runpod-entrypoint.sh

@@ -0,0 +1,21 @@
+#!/bin/bash
+
+# Export specific ENV variables to /etc/rp_environment
+echo "Exporting environment variables..."
+printenv | grep -E '^RUNPOD_|^PATH=|^_=' | sed 's/^\(.*\)=\(.*\)$/export \1="\2"/' >> /etc/rp_environment
+echo 'source /etc/rp_environment' >> ~/.bashrc
+
+if [[ $PUBLIC_KEY ]]
+then
+    mkdir -p ~/.ssh
+    chmod 700 ~/.ssh
+    echo $PUBLIC_KEY >> ~/.ssh/authorized_keys
+    chmod 700 -R ~/.ssh
+    # Start the SSH service in the background
+    service ssh start
+else
+    echo "No PUBLIC_KEY ENV variable provided, not starting openSSH daemon"
+fi
+
+# Execute the passed arguments (CMD)
+exec "$@"

setup.py

@@ -1,27 +1,58 @@
-from setuptools import setup, find_packages
+"""setup.py for axolotl"""
+
+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:
+            if line.startswith("--extra-index-url"):
+                # Handle custom index URLs
+                _, url = line.split()
+                _dependency_links.append(url)
+            elif (
+                "flash-attn" not in line
+                and "deepspeed" not in line
+                and line
+                and line[0] != "#"
+            ):
+                # Handle standard packages
+                _install_requires.append(line)
+
+    # TODO(wing) remove once xformers release supports torch 2.1.0
+    if "torch==2.1.0" in _install_requires:
+        _install_requires.pop(_install_requires.index("xformers>=0.0.22"))
+        _install_requires.append(
+            "xformers @ git+https://github.com/facebookresearch/xformers.git@main"
+        )
+
+    return _install_requires, _dependency_links
+
+
+install_requires, dependency_links = parse_requirements()
 
-install_requires = []
-with open("./requirements.txt", "r") 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[0] != "#"]
-    for r in reqs:
-        install_requires.append(r)
 
 setup(
-    name='axolotl',
-    version='0.1',
-    description="You know you're going to axolotl questions",
-    package_dir={'': 'src'},
+    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.",
+    package_dir={"": "src"},
     packages=find_packages(),
     install_requires=install_requires,
+    dependency_links=dependency_links,
     extras_require={
-        'int4': [
-            "alpaca_lora_4bit @ git+https://github.com/winglian/alpaca_lora_4bit.git@setup_pip",
+        "flash-attn": [
+            "flash-attn==2.3.3",
         ],
-        'int4_triton': [
-            "alpaca_lora_4bit[triton] @ git+https://github.com/winglian/alpaca_lora_4bit.git@setup_pip",
+        "deepspeed": [
+            "deepspeed",
+        ],
+        "mamba-ssm": [
+            "mamba-ssm==1.0.1",
         ],
     },
 )