Compare commits
1 Commits
zero3-8bit
...
phi-moe
| Author | SHA1 | Date | |
|---|---|---|---|
|
cb8bfab9cc |
4
.github/workflows/pypi.yml
vendored
4
.github/workflows/pypi.yml
vendored
@@ -56,9 +56,9 @@ jobs:
|
||||
run: |
|
||||
sed -i -E 's/version="([0-9.]+)",/version="${{ steps.tag.outputs.TAG_NAME }}",/g' setup.py
|
||||
|
||||
- name: Build a source dist
|
||||
- name: Build a binary wheel
|
||||
run: |
|
||||
python setup.py sdist
|
||||
python setup.py sdist bdist_wheel
|
||||
|
||||
- name: Publish package distributions to PyPI
|
||||
uses: pypa/gh-action-pypi-publish@release/v1
|
||||
|
||||
2
.github/workflows/tests.yml
vendored
2
.github/workflows/tests.yml
vendored
@@ -71,7 +71,7 @@ jobs:
|
||||
|
||||
- name: Run tests
|
||||
run: |
|
||||
pytest -n8 --ignore=tests/e2e/ tests/
|
||||
pytest --ignore=tests/e2e/ tests/
|
||||
|
||||
- name: cleanup pip cache
|
||||
run: |
|
||||
|
||||
23
README.md
23
README.md
@@ -1,21 +1,8 @@
|
||||
<p align="center">
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="image/axolotl_logo_digital_white.svg">
|
||||
<source media="(prefers-color-scheme: light)" srcset="image/axolotl_logo_digital_black.svg">
|
||||
<img alt="Axolotl" src="image/axolotl_logo_digital_black.svg" width="400" height="104" style="max-width: 100%;">
|
||||
</picture>
|
||||
</p>
|
||||
# Axolotl
|
||||
|
||||
<p align="center">
|
||||
<img src="https://img.shields.io/github/license/axolotl-ai-cloud/axolotl.svg?color=blue" alt="GitHub License">
|
||||
<img src="https://github.com/axolotl-ai-cloud/axolotl/actions/workflows/tests.yml/badge.svg" alt="tests">
|
||||
<a href="https://github.com/axolotl-ai-cloud/axolotl/releases"><img src="https://img.shields.io/github/release/axolotl-ai-cloud/axolotl.svg" alt="Releases"></a>
|
||||
<img src="https://img.shields.io/github/stars/axolotl-ai-cloud/axolotl" alt="GitHub Repo stars">
|
||||
</p>
|
||||
<p align="center">
|
||||
<img src="https://github.com/axolotl-ai-cloud/axolotl/actions/workflows/tests-nightly.yml/badge.svg" alt="tests-nightly">
|
||||
<img src="https://github.com/axolotl-ai-cloud/axolotl/actions/workflows/multi-gpu-e2e.yml/badge.svg" alt="multigpu-semi-weekly tests">
|
||||
</p>
|
||||
|
||||
|
||||
|
||||
|
||||
Axolotl is a tool designed to streamline the fine-tuning of various AI models, offering support for multiple configurations and architectures.
|
||||
|
||||
@@ -88,7 +75,7 @@ Features:
|
||||
<td>
|
||||
|
||||
<div align="center">
|
||||
<img src="image/axolotl_symbol_digital_white.svg" alt="axolotl" width="160">
|
||||
<img src="image/axolotl.png" alt="axolotl" width="160">
|
||||
<div>
|
||||
<p>
|
||||
<b>Axolotl provides a unified repository for fine-tuning <br />a variety of AI models with ease</b>
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
pytest -n8 --ignore=tests/e2e/ /workspace/axolotl/tests/
|
||||
pytest -n4 --ignore=tests/e2e/ /workspace/axolotl/tests/
|
||||
pytest -n1 --dist loadfile -v /workspace/axolotl/tests/e2e/patched/ /workspace/axolotl/tests/e2e/integrations/
|
||||
pytest --ignore=tests/e2e/patched/ --ignore=tests/e2e/multigpu/ --ignore=tests/e2e/integrations/ /workspace/axolotl/tests/e2e/
|
||||
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 11 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 24 KiB After Width: | Height: | Size: 11 KiB |
@@ -1,19 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<svg xmlns="http://www.w3.org/2000/svg" version="1.1" viewBox="0 0 1113 283.5">
|
||||
<path fill="#141310" d="M435,234.3l-12.1-48.8h-54.4l-12.1,48.8h-24.7l48.2-185.1h31.6l47.9,185.1h-24.5ZM417.7,164.9l-13.8-55.6c-2.7-10.7-4.8-19.7-6.3-26.9-.9-4.2-1.5-7.5-2-9.9-.5,2.5-1.2,5.8-2,9.9-1.5,7.1-3.6,16.1-6.3,26.7l-13.8,55.9h44.3Z"/>
|
||||
<path fill="#141310" d="M568.2,234.3l-29.9-45.6c-1.2-1.9-2.4-4.1-3.5-6.5-.8-1.7-1.5-3.3-2.1-4.5-.6,1.3-1.4,2.8-2.3,4.5-1.3,2.4-2.6,4.6-4,6.5l-29.9,45.6h-28.5l49.6-71.9-46.5-67.9h28.5l27.6,43.1c1.2,1.9,2.3,3.9,3.4,6.1.7,1.4,1.4,2.7,1.9,3.8.5-1.1,1.1-2.4,1.8-3.8,1.1-2.2,2.2-4.2,3.4-6.1l27.6-43.1h28.5l-46.5,68.2,49.3,71.7h-28.5Z"/>
|
||||
<path fill="#141310" d="M658.6,236.3c-16.7,0-30.2-5-40.1-14.8-9.9-9.8-14.9-23.7-14.9-41.3v-31.7c0-17.7,5-31.7,14.8-41.4,9.8-9.7,23.4-14.7,40.3-14.7s30.4,4.9,40.3,14.7c9.8,9.7,14.8,23.7,14.8,41.4v31.7c0,17.6-5,31.5-14.9,41.3-9.9,9.8-23.4,14.8-40.1,14.8ZM658.6,114.1c-9.5,0-17.1,2.7-22.6,8.1-5.5,5.4-8.3,13.4-8.3,23.8v36.7c0,10.5,2.8,18.5,8.3,23.8,5.5,5.4,13.1,8.1,22.6,8.1s17.3-2.7,22.7-8.1c5.4-5.4,8.2-13.4,8.2-23.9v-36.7c0-10.5-2.8-18.5-8.2-23.9-5.4-5.4-13.1-8.1-22.7-8.1Z"/>
|
||||
<path fill="#141310" d="M860.6,236.3c-16.7,0-30.2-5-40.1-14.8-9.9-9.8-14.9-23.7-14.9-41.3v-31.7c0-17.7,5-31.7,14.8-41.4,9.8-9.7,23.4-14.7,40.3-14.7s30.4,4.9,40.3,14.7c9.8,9.7,14.8,23.7,14.8,41.4v31.7c0,17.6-5,31.5-14.9,41.3-9.9,9.8-23.4,14.8-40.1,14.8ZM860.6,114.1c-9.5,0-17.1,2.7-22.6,8.1-5.5,5.4-8.3,13.4-8.3,23.8v36.7c0,10.5,2.8,18.5,8.3,23.8,5.5,5.4,13.1,8.1,22.6,8.1s17.3-2.7,22.7-8.1c5.4-5.4,8.2-13.4,8.2-23.9v-36.7c0-10.5-2.8-18.5-8.2-23.9-5.4-5.4-13.1-8.1-22.7-8.1Z"/>
|
||||
<path fill="#141310" d="M773.9,234c-18,0-32.6-14.6-32.6-32.6V48.8h24.1v152.6c0,4.7,3.8,8.5,8.5,8.5h16.8v24.1h-16.8Z"/>
|
||||
<path fill="#141310" d="M1036.2,234.3V81.4c0-4.7-3.8-8.5-8.5-8.5h-16.8v-24.1h16.8c18,0,32.6,14.6,32.6,32.6v152.9h-24.1Z"/>
|
||||
<path fill="#141310" d="M978.6,234.3c-18,0-32.6-14.6-32.6-32.6v-85.1h-20.3v-22.1h20.3v-45.3h24.1v45.3h30.2v22.1h-30.2v85.1c0,4.7,3.8,8.5,8.5,8.5h21.7v24.1h-21.7Z"/>
|
||||
<path fill="#141310" d="M51.5,49h12.2v-20.6h-12.2c-16,0-29,13-29,29v32.8h20.6v-32.8c0-4.7,3.8-8.4,8.4-8.4Z"/>
|
||||
<path fill="#141310" d="M92.8,49h12.2v-20.6h-12.2c-16,0-29,13-29,29v12.2h20.6v-12.2c0-4.7,3.8-8.4,8.4-8.4Z"/>
|
||||
<path fill="#141310" d="M249.3,57.4c0-16-13-29-29-29h-12.2v20.6h12.2c4.7,0,8.4,3.8,8.4,8.4v32.8h20.6v-32.8Z"/>
|
||||
<path fill="#141310" d="M187.4,90.2v-20.6h-103.1v20.6h-41.2v20.6h-20.6v41.2c0,11.4,9.2,20.6,20.6,20.6h185.5c11.4,0,20.6-9.2,20.6-20.6v-41.2h-20.6v-20.6h-41.2ZM166.8,141.7c0-5.7-4.6-10.3-10.3-10.3s-10.3,4.6-10.3,10.3v10.3h-20.6v-20.6c0-11.4,9.2-20.6,20.6-20.6s20.6,9.2,20.6,20.6v10.3ZM228.7,141.7c0-5.7-4.6-10.3-10.3-10.3s-10.3,4.6-10.3,10.3v10.3h-20.6v-20.6c0-11.4,9.2-20.6,20.6-20.6s20.6,9.2,20.6,20.6v10.3Z"/>
|
||||
<path fill="#141310" d="M208,57.4c0-16-13-29-29-29h-12.2v20.6h12.2c4.7,0,8.4,3.8,8.4,8.4v12.2h20.6v-12.2Z"/>
|
||||
<rect fill="#141310" x="22.5" y="234.5" width="41.2" height="20.6"/>
|
||||
<rect fill="#141310" x="84.3" y="234.5" width="164.9" height="20.6"/>
|
||||
<rect fill="#141310" x="208" y="193.3" width="41.2" height="20.6"/>
|
||||
<rect fill="#141310" x="22.5" y="193.3" width="164.9" height="20.6"/>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 3.2 KiB |
@@ -1,11 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<svg xmlns="http://www.w3.org/2000/svg" version="1.1" viewBox="0 0 1113 283.5">
|
||||
<path fill="#fff" d="M462.9,234.2l-12.1-48.8h-54.4l-12.1,48.8h-24.7l48.2-185h31.6l47.9,185h-24.4ZM445.7,164.8l-13.8-55.6c-2.7-10.7-4.8-19.7-6.3-26.9-.9-4.2-1.5-7.5-2-9.9-.5,2.5-1.2,5.8-2,9.9-1.5,7.1-3.6,16.1-6.3,26.7l-13.8,55.9h44.3Z"/>
|
||||
<path fill="#fff" d="M596.1,234.2l-29.9-45.6c-1.2-1.9-2.4-4.1-3.5-6.5-.8-1.7-1.5-3.3-2.1-4.5-.6,1.3-1.4,2.8-2.3,4.5-1.3,2.4-2.6,4.6-4,6.5l-29.9,45.6h-28.5l49.5-71.9-46.5-67.9h28.5l27.6,43.1c1.2,1.9,2.3,3.9,3.4,6.1.7,1.4,1.3,2.7,1.9,3.8.5-1.1,1.1-2.4,1.8-3.8,1.1-2.2,2.2-4.2,3.4-6.1l27.6-43.1h28.5l-46.5,68.1,49.3,71.6h-28.5Z"/>
|
||||
<path fill="#fff" d="M686.4,236.2c-16.7,0-30.2-5-40.1-14.8-9.9-9.8-14.9-23.7-14.9-41.3v-31.7c0-17.7,5-31.6,14.8-41.4,9.8-9.7,23.4-14.7,40.2-14.7s30.4,4.9,40.2,14.7c9.8,9.7,14.8,23.7,14.8,41.4v31.7c0,17.6-5,31.4-14.9,41.3-9.9,9.8-23.4,14.8-40.1,14.8ZM686.4,114.1c-9.5,0-17.1,2.7-22.6,8.1-5.5,5.4-8.3,13.4-8.3,23.8v36.7c0,10.5,2.8,18.5,8.3,23.8,5.5,5.4,13.1,8.1,22.6,8.1s17.3-2.7,22.7-8.1c5.4-5.4,8.2-13.4,8.2-23.8v-36.7c0-10.5-2.8-18.5-8.2-23.8-5.4-5.4-13.1-8.1-22.7-8.1Z"/>
|
||||
<path fill="#fff" d="M888.3,236.2c-16.7,0-30.2-5-40.1-14.8-9.9-9.8-14.9-23.7-14.9-41.3v-31.7c0-17.7,5-31.6,14.8-41.4,9.8-9.7,23.4-14.7,40.2-14.7s30.4,4.9,40.2,14.7c9.8,9.7,14.8,23.7,14.8,41.4v31.7c0,17.6-5,31.4-14.9,41.3-9.9,9.8-23.4,14.8-40.1,14.8ZM888.3,114.1c-9.5,0-17.1,2.7-22.6,8.1-5.5,5.4-8.3,13.4-8.3,23.8v36.7c0,10.5,2.8,18.5,8.3,23.8,5.5,5.4,13.1,8.1,22.6,8.1s17.3-2.7,22.7-8.1c5.4-5.4,8.2-13.4,8.2-23.8v-36.7c0-10.5-2.8-18.5-8.2-23.8-5.4-5.4-13.1-8.1-22.7-8.1Z"/>
|
||||
<path fill="#fff" d="M801.7,234c-18,0-32.6-14.6-32.6-32.6V48.8h24.1v152.5c0,4.7,3.8,8.5,8.5,8.5h16.7v24.1h-16.7Z"/>
|
||||
<path fill="#fff" d="M1063.8,234.2V81.4c0-4.7-3.8-8.5-8.5-8.5h-16.7v-24.1h16.7c18,0,32.6,14.6,32.6,32.6v152.8h-24.1Z"/>
|
||||
<path fill="#fff" d="M1006.2,234.2c-18,0-32.6-14.6-32.6-32.6v-85h-20.3v-22.1h20.3v-45.2h24.1v45.2h30.2v22.1h-30.2v85c0,4.7,3.8,8.5,8.5,8.5h21.7v24.1h-21.7Z"/>
|
||||
<path fill="#fff" d="M160.2,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM222,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM222,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM160.2,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM160.2,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM222,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM222,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM160.2,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM160.2,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM222,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM222,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM160.2,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM277.3,57.4c0-23.8-19.3-43.1-43.1-43.1h-12.2c-3.9,0-7.6,1.6-10.2,4.4-5.9-2.9-12.3-4.4-18.9-4.4h-12.2c-7.7,0-14.1,6.3-14.1,14.1v20.6c0,2.4.6,4.6,1.6,6.6h-37c1-2,1.6-4.2,1.6-6.6v-20.6c0-7.7-6.3-14.1-14.1-14.1h-12.2c-6.5,0-13,1.5-18.9,4.4-2.6-2.8-6.3-4.4-10.2-4.4h-12.2c-23.8,0-43.1,19.3-43.1,43.1v32.8c0,4.1,1.7,7.7,4.5,10.3-2.8,2.6-4.5,6.2-4.5,10.3v41.2c0,11,5.2,20.8,13.2,27.2-7.3.4-13.2,6.6-13.2,14v20.6c0,4.1,1.7,7.7,4.5,10.3-2.8,2.6-4.5,6.2-4.5,10.3v20.6c0,7.7,6.3,14.1,14.1,14.1h41.2c4.1,0,7.7-1.7,10.3-4.5,2.6,2.8,6.2,4.5,10.3,4.5h164.9c7.7,0,14.1-6.3,14.1-14.1v-20.6c0-4.1-1.7-7.7-4.5-10.3,2.8-2.6,4.5-6.2,4.5-10.3v-20.6c0-7.5-5.8-13.6-13.2-14,8-6.4,13.2-16.2,13.2-27.2v-41.2c0-4.1-1.7-7.7-4.5-10.3,2.8-2.6,4.5-6.2,4.5-10.3v-32.8ZM77.8,255.1h-41.2v-20.6h41.2v20.6ZM36.5,213.9v-20.6h164.9v20.6H36.5ZM263.3,255.1H98.4v-20.6h164.9v20.6ZM263.3,213.9h-41.2v-20.6h41.2v20.6ZM263.3,90.2h-20.6v20.6h20.6v41.2c0,11.4-9.2,20.6-20.6,20.6H57.2c-11.4,0-20.6-9.2-20.6-20.6v-41.2h20.6v-20.6h-20.6v-32.8c0-16,13-29,29-29h12.2v20.6h-12.2c-4.7,0-8.4,3.8-8.4,8.4v32.8h41.2v-20.6h-20.6v-12.2c0-16,13-29,29-29h12.2v20.6h-12.2c-4.7,0-8.4,3.8-8.4,8.4v12.2h103.1v-12.2c0-4.7-3.8-8.4-8.4-8.4h-12.2v-20.6h12.2c16,0,29,13,29,29v12.2h-20.6v20.6h41.2v-32.8c0-4.7-3.8-8.4-8.4-8.4h-12.2v-20.6h12.2c16,0,29,13,29,29v32.8ZM201.4,152h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6s-20.6,9.2-20.6,20.6v20.6ZM160.2,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM160.2,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM222,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM222,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM160.2,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM160.2,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM222,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM222,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM160.2,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM160.2,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM222,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM222,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM160.2,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6Z"/>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 6.6 KiB |
@@ -1,26 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<svg xmlns="http://www.w3.org/2000/svg" version="1.1" viewBox="0 0 283.5 283.5">
|
||||
<defs>
|
||||
<style>
|
||||
.cls-1 {
|
||||
fill: #141310;
|
||||
}
|
||||
</style>
|
||||
</defs>
|
||||
<!-- Generator: Adobe Illustrator 28.7.1, SVG Export Plug-In . SVG Version: 1.2.0 Build 142) -->
|
||||
<g>
|
||||
<g id="Layer_1">
|
||||
<g>
|
||||
<path class="cls-1" d="M46.9,37.4h13.7V14.2h-13.7c-18,0-32.7,14.6-32.7,32.7v36.9h23.2v-36.9c0-5.2,4.2-9.5,9.5-9.5Z"/>
|
||||
<path class="cls-1" d="M93.2,37.4h13.7V14.2h-13.7c-18,0-32.7,14.6-32.7,32.7v13.7h23.2v-13.7c0-5.2,4.2-9.5,9.5-9.5Z"/>
|
||||
<path class="cls-1" d="M269.3,46.9c0-18-14.6-32.7-32.7-32.7h-13.7v23.2h13.7c5.2,0,9.5,4.2,9.5,9.5v36.9h23.2v-36.9Z"/>
|
||||
<path class="cls-1" d="M199.7,83.8v-23.2h-116v23.2h-46.4v23.2H14.2v46.4c0,12.8,10.4,23.2,23.2,23.2h208.7c12.8,0,23.2-10.4,23.2-23.2v-46.4h-23.2v-23.2h-46.4ZM176.5,141.7c0-6.4-5.2-11.6-11.6-11.6s-11.6,5.2-11.6,11.6v11.6h-23.2v-23.2c0-12.8,10.4-23.2,23.2-23.2s23.2,10.4,23.2,23.2v11.6ZM246.1,141.7c0-6.4-5.2-11.6-11.6-11.6s-11.6,5.2-11.6,11.6v11.6h-23.2v-23.2c0-12.8,10.4-23.2,23.2-23.2s23.2,10.4,23.2,23.2v11.6Z"/>
|
||||
<path class="cls-1" d="M222.9,46.9c0-18-14.6-32.7-32.7-32.7h-13.7v23.2h13.7c5.2,0,9.5,4.2,9.5,9.5v13.7h23.2v-13.7Z"/>
|
||||
<rect class="cls-1" x="14.2" y="246.1" width="46.4" height="23.2"/>
|
||||
<rect class="cls-1" x="83.8" y="246.1" width="185.5" height="23.2"/>
|
||||
<rect class="cls-1" x="222.9" y="199.7" width="46.4" height="23.2"/>
|
||||
<rect class="cls-1" x="14.2" y="199.7" width="185.5" height="23.2"/>
|
||||
</g>
|
||||
</g>
|
||||
</g>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 1.6 KiB |
@@ -1,16 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<svg xmlns="http://www.w3.org/2000/svg" version="1.1" viewBox="0 0 283.5 283.5">
|
||||
<defs>
|
||||
<style>
|
||||
.cls-1 {
|
||||
fill: #fff;
|
||||
}
|
||||
</style>
|
||||
</defs>
|
||||
<!-- Generator: Adobe Illustrator 28.7.1, SVG Export Plug-In . SVG Version: 1.2.0 Build 142) -->
|
||||
<g>
|
||||
<g id="Layer_1">
|
||||
<path class="cls-1" d="M152,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM214,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM214,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM152,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM152,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM214,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM214,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM152,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM152,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM214,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM214,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM152,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM269.3,57.3c0-23.8-19.4-43.1-43.1-43.1h-12.2c-3.9,0-7.6,1.6-10.2,4.4-5.9-2.9-12.3-4.4-18.9-4.4h-12.2c-7.8,0-14.1,6.3-14.1,14.1v20.6c0,2.4.6,4.6,1.6,6.6h-37c1-2,1.6-4.2,1.6-6.6v-20.6c0-7.8-6.3-14.1-14.1-14.1h-12.2c-6.6,0-13,1.5-18.9,4.4-2.6-2.8-6.3-4.4-10.2-4.4h-12.2c-23.8,0-43.1,19.4-43.1,43.1v32.8c0,4.1,1.7,7.7,4.5,10.3-2.8,2.6-4.5,6.2-4.5,10.3v41.3c0,11,5.2,20.9,13.2,27.2-7.4.4-13.2,6.6-13.2,14v20.6c0,4.1,1.7,7.7,4.5,10.3-2.8,2.6-4.5,6.2-4.5,10.3v20.6c0,7.8,6.3,14.1,14.1,14.1h41.3c4.1,0,7.7-1.7,10.3-4.5,2.6,2.8,6.2,4.5,10.3,4.5h165.1c7.8,0,14.1-6.3,14.1-14.1v-20.6c0-4.1-1.7-7.7-4.5-10.3,2.8-2.6,4.5-6.2,4.5-10.3v-20.6c0-7.5-5.9-13.6-13.2-14,8-6.4,13.2-16.2,13.2-27.2v-41.3c0-4.1-1.7-7.7-4.5-10.3,2.8-2.6,4.5-6.2,4.5-10.3v-32.8ZM69.5,255.2H28.2v-20.6h41.3v20.6ZM28.2,214v-20.6h165.1v20.6H28.2ZM255.2,255.2H90.1v-20.6h165.1v20.6ZM255.2,214h-41.3v-20.6h41.3v20.6ZM255.2,90.1h-20.6v20.6h20.6v41.3c0,11.4-9.2,20.6-20.6,20.6H48.9c-11.4,0-20.6-9.2-20.6-20.6v-41.3h20.6v-20.6h-20.6v-32.8c0-16.1,13-29.1,29.1-29.1h12.2v20.6h-12.2c-4.7,0-8.4,3.8-8.4,8.4v32.8h41.3v-20.6h-20.6v-12.2c0-16.1,13-29.1,29.1-29.1h12.2v20.6h-12.2c-4.7,0-8.4,3.8-8.4,8.4v12.2h103.2v-12.2c0-4.7-3.8-8.4-8.4-8.4h-12.2v-20.6h12.2c16.1,0,29.1,13,29.1,29.1v12.2h-20.6v20.6h41.3v-32.8c0-4.7-3.8-8.4-8.4-8.4h-12.2v-20.6h12.2c16.1,0,29.1,13,29.1,29.1v32.8ZM193.3,152h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6s-20.6,9.2-20.6,20.6v20.6ZM152,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM152,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM214,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM214,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM152,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM152,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM214,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM214,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM152,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM152,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM214,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM214,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6ZM152,110.8c-11.4,0-20.6,9.2-20.6,20.6v20.6h20.6v-10.3c0-5.7,4.6-10.3,10.3-10.3s10.3,4.6,10.3,10.3v-10.3c0-11.4-9.2-20.6-20.6-20.6Z"/>
|
||||
</g>
|
||||
</g>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 5.0 KiB |
@@ -1,17 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<svg xmlns="http://www.w3.org/2000/svg" version="1.1" viewBox="0 0 765.4 212.6">
|
||||
<!-- Generator: Adobe Illustrator 28.7.1, SVG Export Plug-In . SVG Version: 1.2.0 Build 142) -->
|
||||
<g>
|
||||
<g id="Layer_1">
|
||||
<g>
|
||||
<path d="M121.6,198.1l-12.1-48.8h-54.4l-12.1,48.8h-24.7L66.6,12.9h31.6l47.9,185.1h-24.5ZM104.4,128.6l-13.8-55.6c-2.7-10.7-4.8-19.7-6.3-26.9-.9-4.2-1.5-7.5-2-9.9-.5,2.5-1.2,5.8-2,9.9-1.5,7.1-3.6,16.1-6.3,26.7l-13.8,55.9h44.3Z"/>
|
||||
<path d="M254.9,198.1l-29.9-45.6c-1.2-1.9-2.4-4.1-3.5-6.5-.8-1.7-1.5-3.3-2.1-4.5-.6,1.3-1.4,2.8-2.3,4.5-1.3,2.4-2.6,4.6-4,6.5l-29.9,45.6h-28.5l49.6-71.9-46.5-67.9h28.5l27.6,43.1c1.2,1.9,2.3,3.9,3.4,6.1.7,1.4,1.4,2.7,1.9,3.8.5-1.1,1.1-2.4,1.8-3.8,1.1-2.2,2.2-4.2,3.4-6.1l27.6-43.1h28.5l-46.5,68.2,49.3,71.7h-28.5Z"/>
|
||||
<path d="M345.2,200.1c-16.7,0-30.2-5-40.1-14.8-9.9-9.8-14.9-23.7-14.9-41.3v-31.7c0-17.7,5-31.7,14.8-41.4,9.8-9.7,23.4-14.7,40.3-14.7s30.4,4.9,40.3,14.7c9.8,9.7,14.8,23.7,14.8,41.4v31.7c0,17.6-5,31.5-14.9,41.3-9.9,9.8-23.4,14.8-40.1,14.8ZM345.2,77.8c-9.5,0-17.1,2.7-22.6,8.1-5.5,5.4-8.3,13.4-8.3,23.8v36.7c0,10.5,2.8,18.5,8.3,23.8,5.5,5.4,13.1,8.1,22.6,8.1s17.3-2.7,22.7-8.1c5.4-5.4,8.2-13.4,8.2-23.9v-36.7c0-10.5-2.8-18.5-8.2-23.9-5.4-5.4-13.1-8.1-22.7-8.1Z"/>
|
||||
<path d="M547.3,200.1c-16.7,0-30.2-5-40.1-14.8-9.9-9.8-14.9-23.7-14.9-41.3v-31.7c0-17.7,5-31.7,14.8-41.4,9.8-9.7,23.4-14.7,40.3-14.7s30.4,4.9,40.3,14.7c9.8,9.7,14.8,23.7,14.8,41.4v31.7c0,17.6-5,31.5-14.9,41.3-9.9,9.8-23.4,14.8-40.1,14.8ZM547.3,77.8c-9.5,0-17.1,2.7-22.6,8.1-5.5,5.4-8.3,13.4-8.3,23.8v36.7c0,10.5,2.8,18.5,8.3,23.8,5.5,5.4,13.1,8.1,22.6,8.1s17.3-2.7,22.7-8.1c5.4-5.4,8.2-13.4,8.2-23.9v-36.7c0-10.5-2.8-18.5-8.2-23.9-5.4-5.4-13.1-8.1-22.7-8.1Z"/>
|
||||
<path d="M460.6,197.8c-18,0-32.6-14.6-32.6-32.6V12.5h24.1v152.6c0,4.7,3.8,8.5,8.5,8.5h16.8v24.1h-16.8Z"/>
|
||||
<path d="M722.8,198.1V45.2c0-4.7-3.8-8.5-8.5-8.5h-16.8V12.5h16.8c18,0,32.6,14.6,32.6,32.6v152.9h-24.1Z"/>
|
||||
<path d="M665.2,198.1c-18,0-32.6-14.6-32.6-32.6v-85.1h-20.3v-22.1h20.3V12.9h24.1v45.3h30.2v22.1h-30.2v85.1c0,4.7,3.8,8.5,8.5,8.5h21.7v24.1h-21.7Z"/>
|
||||
</g>
|
||||
</g>
|
||||
</g>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 2.1 KiB |
@@ -1,24 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<svg xmlns="http://www.w3.org/2000/svg" version="1.1" viewBox="0 0 765.4 212.6">
|
||||
<defs>
|
||||
<style>
|
||||
.cls-1 {
|
||||
fill: #fff;
|
||||
}
|
||||
</style>
|
||||
</defs>
|
||||
<!-- Generator: Adobe Illustrator 28.7.1, SVG Export Plug-In . SVG Version: 1.2.0 Build 142) -->
|
||||
<g>
|
||||
<g id="Layer_1">
|
||||
<g>
|
||||
<path class="cls-1" d="M121.6,198.1l-12.1-48.8h-54.4l-12.1,48.8h-24.7L66.6,12.9h31.6l47.9,185.1h-24.5ZM104.4,128.6l-13.8-55.6c-2.7-10.7-4.8-19.7-6.3-26.9-.9-4.2-1.5-7.5-2-9.9-.5,2.5-1.2,5.8-2,9.9-1.5,7.1-3.6,16.1-6.3,26.7l-13.8,55.9h44.3Z"/>
|
||||
<path class="cls-1" d="M254.9,198.1l-29.9-45.6c-1.2-1.9-2.4-4.1-3.5-6.5-.8-1.7-1.5-3.3-2.1-4.5-.6,1.3-1.4,2.8-2.3,4.5-1.3,2.4-2.6,4.6-4,6.5l-29.9,45.6h-28.5l49.6-71.9-46.5-67.9h28.5l27.6,43.1c1.2,1.9,2.3,3.9,3.4,6.1.7,1.4,1.4,2.7,1.9,3.8.5-1.1,1.1-2.4,1.8-3.8,1.1-2.2,2.2-4.2,3.4-6.1l27.6-43.1h28.5l-46.5,68.2,49.3,71.7h-28.5Z"/>
|
||||
<path class="cls-1" d="M345.2,200.1c-16.7,0-30.2-5-40.1-14.8-9.9-9.8-14.9-23.7-14.9-41.3v-31.7c0-17.7,5-31.7,14.8-41.4,9.8-9.7,23.4-14.7,40.3-14.7s30.4,4.9,40.3,14.7c9.8,9.7,14.8,23.7,14.8,41.4v31.7c0,17.6-5,31.5-14.9,41.3-9.9,9.8-23.4,14.8-40.1,14.8ZM345.2,77.8c-9.5,0-17.1,2.7-22.6,8.1-5.5,5.4-8.3,13.4-8.3,23.8v36.7c0,10.5,2.8,18.5,8.3,23.8,5.5,5.4,13.1,8.1,22.6,8.1s17.3-2.7,22.7-8.1c5.4-5.4,8.2-13.4,8.2-23.9v-36.7c0-10.5-2.8-18.5-8.2-23.9-5.4-5.4-13.1-8.1-22.7-8.1Z"/>
|
||||
<path class="cls-1" d="M547.3,200.1c-16.7,0-30.2-5-40.1-14.8-9.9-9.8-14.9-23.7-14.9-41.3v-31.7c0-17.7,5-31.7,14.8-41.4,9.8-9.7,23.4-14.7,40.3-14.7s30.4,4.9,40.3,14.7c9.8,9.7,14.8,23.7,14.8,41.4v31.7c0,17.6-5,31.5-14.9,41.3-9.9,9.8-23.4,14.8-40.1,14.8ZM547.3,77.8c-9.5,0-17.1,2.7-22.6,8.1-5.5,5.4-8.3,13.4-8.3,23.8v36.7c0,10.5,2.8,18.5,8.3,23.8,5.5,5.4,13.1,8.1,22.6,8.1s17.3-2.7,22.7-8.1c5.4-5.4,8.2-13.4,8.2-23.9v-36.7c0-10.5-2.8-18.5-8.2-23.9-5.4-5.4-13.1-8.1-22.7-8.1Z"/>
|
||||
<path class="cls-1" d="M460.6,197.8c-18,0-32.6-14.6-32.6-32.6V12.5h24.1v152.6c0,4.7,3.8,8.5,8.5,8.5h16.8v24.1h-16.8Z"/>
|
||||
<path class="cls-1" d="M722.8,198.1V45.2c0-4.7-3.8-8.5-8.5-8.5h-16.8V12.5h16.8c18,0,32.6,14.6,32.6,32.6v152.9h-24.1Z"/>
|
||||
<path class="cls-1" d="M665.2,198.1c-18,0-32.6-14.6-32.6-32.6v-85.1h-20.3v-22.1h20.3V12.9h24.1v45.3h30.2v22.1h-30.2v85.1c0,4.7,3.8,8.5,8.5,8.5h21.7v24.1h-21.7Z"/>
|
||||
</g>
|
||||
</g>
|
||||
</g>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 2.3 KiB |
@@ -31,7 +31,7 @@ art
|
||||
gradio==3.50.2
|
||||
tensorboard
|
||||
python-dotenv==1.0.1
|
||||
autoawq==0.2.7.post2
|
||||
autoawq>=0.2.5
|
||||
triton>=2.3.0
|
||||
liger-kernel==0.4.1
|
||||
|
||||
|
||||
@@ -10,6 +10,7 @@ MOE_ARCH_BLOCK = {
|
||||
"JetMoeMoE",
|
||||
],
|
||||
"mixtral": "MixtralSparseMoeBlock",
|
||||
"phimoe": "PhiMoESparseMoeBlock",
|
||||
"qwen2_moe": "Qwen2MoeSparseMoeBlock",
|
||||
"deepseek_v2": "DeepseekV2MoE",
|
||||
}
|
||||
|
||||
@@ -1,83 +0,0 @@
|
||||
"""
|
||||
fix for zero3 8-bit lora
|
||||
see https://github.com/huggingface/transformers/pull/32943/files
|
||||
"""
|
||||
import inspect
|
||||
import logging
|
||||
|
||||
from transformers import modeling_utils
|
||||
|
||||
LOG = logging.getLogger("axolotl.monkeypatch.modeling_zero3_int8_lora")
|
||||
|
||||
ORIGINAL_LOAD_CODE = """
|
||||
if is_fsdp_enabled() or is_deepspeed_zero3_enabled():
|
||||
module, tensor_name = get_module_from_name(model, param_name)
|
||||
value = getattr(module, tensor_name)
|
||||
param_to = "cpu"
|
||||
if is_fsdp_enabled() and not is_local_dist_rank_0():
|
||||
param_to = "meta"
|
||||
value = type(value)(value.data.to(param_to), **value.__dict__)
|
||||
setattr(module, tensor_name, value)
|
||||
"""
|
||||
|
||||
PATCHED_LOAD_CODE = """
|
||||
if is_fsdp_enabled() or is_deepspeed_zero3_enabled():
|
||||
module, tensor_name = get_module_from_name(model, param_name)
|
||||
value = getattr(module, tensor_name)
|
||||
param_to = "cpu"
|
||||
if is_fsdp_enabled() and not is_local_dist_rank_0():
|
||||
param_to = "meta"
|
||||
val_kwargs = {}
|
||||
if hasattr(module, "weight") and module.weight.__class__.__name__ == "Int8Params":
|
||||
val_kwargs["requires_grad"] = False
|
||||
value = type(value)(value.data.to(param_to), **val_kwargs, **value.__dict__)
|
||||
setattr(module, tensor_name, value)
|
||||
"""
|
||||
|
||||
|
||||
def get_modeling_state_dict_code() -> str:
|
||||
load_code = inspect.getsource(
|
||||
modeling_utils._load_state_dict_into_meta_model # pylint: disable=protected-access
|
||||
)
|
||||
return load_code
|
||||
|
||||
|
||||
def check_modeling_state_dict_code_is_patchable() -> bool:
|
||||
load_code = get_modeling_state_dict_code()
|
||||
return ORIGINAL_LOAD_CODE in load_code
|
||||
|
||||
|
||||
def patch_modeling_state_dict_code():
|
||||
"""
|
||||
monkeypatch for fixing the meta model loader for zero3 8-bit lora
|
||||
"""
|
||||
|
||||
load_code = get_modeling_state_dict_code()
|
||||
modeling_utils._original_load_state_dict_into_meta_model = ( # pylint: disable=protected-access
|
||||
load_code
|
||||
)
|
||||
assert (
|
||||
ORIGINAL_LOAD_CODE in load_code
|
||||
), "Original _load_state_dict_into_meta_model code not found"
|
||||
|
||||
load_code = load_code.replace(ORIGINAL_LOAD_CODE, PATCHED_LOAD_CODE)
|
||||
load_code = load_code.replace(
|
||||
"def _load_state_dict_into_meta_model(",
|
||||
"def _fixed_load_state_dict_into_meta_model(",
|
||||
1,
|
||||
)
|
||||
|
||||
items_to_import = []
|
||||
for item in dir(modeling_utils):
|
||||
if item in load_code:
|
||||
items_to_import.append(item)
|
||||
|
||||
exec( # pylint: disable=exec-used # nosec B102
|
||||
"from transformers.modeling_utils import ("
|
||||
+ ", ".join(x for x in items_to_import)
|
||||
+ ")",
|
||||
globals(),
|
||||
)
|
||||
exec(load_code, globals()) # pylint: disable=exec-used # nosec B102
|
||||
LOG.info("patching _load_state_dict_into_meta_model")
|
||||
modeling_utils._load_state_dict_into_meta_model = _fixed_load_state_dict_into_meta_model # pylint: disable=protected-access,undefined-variable # noqa: F821
|
||||
@@ -20,6 +20,7 @@ SUPPORTED_MULTIPACK_MODEL_TYPES = [
|
||||
"falcon",
|
||||
"phi",
|
||||
"phi3",
|
||||
"phimoe",
|
||||
"gemma",
|
||||
"gemma2",
|
||||
"gemmoe",
|
||||
|
||||
@@ -437,15 +437,6 @@ def setup_deepspeed_env(cfg, stage=None):
|
||||
os.environ["ACCELERATE_DEEPSPEED_ZERO_STAGE"] = str(stage)
|
||||
if stage == 3:
|
||||
os.environ["ACCELERATE_DEEPSPEED_ZERO3_INIT"] = "true"
|
||||
if cfg.adapter and cfg.load_in_8bit:
|
||||
from axolotl.monkeypatch.modeling_zero3_int8_lora import (
|
||||
patch_modeling_state_dict_code,
|
||||
)
|
||||
|
||||
try:
|
||||
patch_modeling_state_dict_code()
|
||||
except AssertionError:
|
||||
LOG.warning("Failed to patch the meta model loading code")
|
||||
# If we don't assign this, it doesn't actually get set in the accelerate weakref
|
||||
_ = HfTrainerDeepSpeedConfig(cfg.deepspeed)
|
||||
|
||||
|
||||
@@ -5,25 +5,6 @@ import shutil
|
||||
import tempfile
|
||||
|
||||
import pytest
|
||||
from huggingface_hub import snapshot_download
|
||||
|
||||
|
||||
@pytest.fixture(scope="session", autouse=True)
|
||||
def download_smollm2_135m_model():
|
||||
# download the model
|
||||
snapshot_download("HuggingFaceTB/SmolLM2-135M")
|
||||
|
||||
|
||||
@pytest.fixture(scope="session", autouse=True)
|
||||
def download_tatsu_lab_alpaca_dataset():
|
||||
# download the model
|
||||
snapshot_download("tatsu-lab/alpaca", repo_type="dataset")
|
||||
|
||||
|
||||
@pytest.fixture(scope="session", autouse=True)
|
||||
def download_mhenrichsen_alpaca_2k_dataset():
|
||||
# download the model
|
||||
snapshot_download("mhenrichsen/alpaca_2k_test", repo_type="dataset")
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
|
||||
@@ -25,7 +25,7 @@ AXOLOTL_ROOT = Path(__file__).parent.parent.parent.parent
|
||||
@pytest.fixture(scope="session", autouse=True)
|
||||
def download_model():
|
||||
# download the model
|
||||
snapshot_download("HuggingFaceTB/SmolLM2-135M")
|
||||
snapshot_download("TinyLlama/TinyLlama_v1.1")
|
||||
|
||||
|
||||
class TestMultiGPULlama:
|
||||
@@ -37,7 +37,7 @@ class TestMultiGPULlama:
|
||||
# pylint: disable=duplicate-code
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "HuggingFaceTB/SmolLM2-135M",
|
||||
"base_model": "HuggingFaceTB/SmolLM-135M",
|
||||
"sequence_len": 2048,
|
||||
"adapter": "lora",
|
||||
"lora_r": 8,
|
||||
@@ -93,7 +93,7 @@ class TestMultiGPULlama:
|
||||
# pylint: disable=duplicate-code
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "HuggingFaceTB/SmolLM2-135M",
|
||||
"base_model": "HuggingFaceTB/SmolLM-135M",
|
||||
"sequence_len": 2048,
|
||||
"sample_packing": True,
|
||||
"eval_sample_packing": False,
|
||||
@@ -149,7 +149,8 @@ class TestMultiGPULlama:
|
||||
# pylint: disable=duplicate-code
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "HuggingFaceTB/SmolLM2-135M",
|
||||
"base_model": "TinyLlama/TinyLlama_v1.1",
|
||||
"tokenizer_type": "LlamaTokenizer",
|
||||
"sequence_len": 2048,
|
||||
"sample_packing": False,
|
||||
"eval_sample_packing": False,
|
||||
@@ -162,10 +163,12 @@ class TestMultiGPULlama:
|
||||
"lora_target_linear": True,
|
||||
"val_set_size": 0.05,
|
||||
"special_tokens": {
|
||||
"pad_token": "<|endoftext|>",
|
||||
"unk_token": "<unk>",
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
},
|
||||
"rl": "dpo",
|
||||
"chat_template": "chatml",
|
||||
"chat_template": "llama3",
|
||||
"datasets": [
|
||||
{
|
||||
"path": "fozziethebeat/alpaca_messages_2k_dpo_test",
|
||||
@@ -218,7 +221,7 @@ class TestMultiGPULlama:
|
||||
# pylint: disable=duplicate-code
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "HuggingFaceTB/SmolLM2-135M",
|
||||
"base_model": "HuggingFaceTB/SmolLM-135M",
|
||||
"sequence_len": 2048,
|
||||
"sample_packing": False,
|
||||
"eval_sample_packing": False,
|
||||
@@ -291,7 +294,7 @@ class TestMultiGPULlama:
|
||||
# pylint: disable=duplicate-code
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "HuggingFaceTB/SmolLM2-135M",
|
||||
"base_model": "HuggingFaceTB/SmolLM-135M",
|
||||
"sequence_len": 2048,
|
||||
"val_set_size": 0.01,
|
||||
"special_tokens": {
|
||||
@@ -356,7 +359,7 @@ class TestMultiGPULlama:
|
||||
# pylint: disable=duplicate-code
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "HuggingFaceTB/SmolLM2-135M",
|
||||
"base_model": "HuggingFaceTB/SmolLM-135M",
|
||||
"sample_packing": True,
|
||||
"pad_to_sequence_len": True,
|
||||
"sequence_len": 2048,
|
||||
@@ -419,7 +422,8 @@ class TestMultiGPULlama:
|
||||
# pylint: disable=duplicate-code
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "axolotl-ai-co/SmolLM2-135M-bnb-nf4-bf16",
|
||||
"base_model": "axolotl-ai-co/TinyLlama_v1.1-bnb-nf4-bf16",
|
||||
"tokenizer_type": "AutoTokenizer",
|
||||
"adapter": "qlora",
|
||||
"mean_resizing_embeddings": True,
|
||||
"load_in_4bit": True,
|
||||
@@ -427,17 +431,17 @@ class TestMultiGPULlama:
|
||||
"lora_alpha": 16,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_target_linear": True,
|
||||
# "lora_modules_to_save": [
|
||||
# "embed_tokens",
|
||||
# "lm_head",
|
||||
# ],
|
||||
"lora_modules_to_save": [
|
||||
"embed_tokens",
|
||||
"lm_head",
|
||||
],
|
||||
"sample_packing": True,
|
||||
"eval_sample_packing": False,
|
||||
"pad_to_sequence_len": True,
|
||||
"sequence_len": 2048,
|
||||
"val_set_size": 0.05,
|
||||
"special_tokens": {
|
||||
"pad_token": "<|endoftext|>",
|
||||
"pad_token": "</s>",
|
||||
},
|
||||
"datasets": [
|
||||
{
|
||||
@@ -499,7 +503,7 @@ class TestMultiGPULlama:
|
||||
# pylint: disable=duplicate-code
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "HuggingFaceTB/SmolLM2-135M",
|
||||
"base_model": "HuggingFaceTB/SmolLM-135M",
|
||||
"sample_packing": True,
|
||||
"pad_to_sequence_len": True,
|
||||
"sequence_len": 2048,
|
||||
@@ -549,7 +553,7 @@ class TestMultiGPULlama:
|
||||
# pylint: disable=duplicate-code
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "HuggingFaceTB/SmolLM2-135M",
|
||||
"base_model": "HuggingFaceTB/SmolLM-135M",
|
||||
"load_in_4bit": True,
|
||||
"adapter": "qlora",
|
||||
"lora_r": 8,
|
||||
@@ -601,61 +605,3 @@ class TestMultiGPULlama:
|
||||
str(Path(temp_dir) / "config.yaml"),
|
||||
]
|
||||
)
|
||||
|
||||
def test_8bit_lora_ds_zero3(self, temp_dir):
|
||||
# pylint: disable=duplicate-code
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "TinyLlama/TinyLlama_v1.1",
|
||||
"load_in_8bit": True,
|
||||
"tokenizer_type": "LlamaTokenizer",
|
||||
"sequence_len": 2048,
|
||||
"sample_packing": True,
|
||||
"eval_sample_packing": False,
|
||||
"pad_to_sequence_len": True,
|
||||
"adapter": "lora",
|
||||
"lora_r": 8,
|
||||
"lora_alpha": 16,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_target_linear": True,
|
||||
"val_set_size": 0.05,
|
||||
"special_tokens": {
|
||||
"unk_token": "<unk>",
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
},
|
||||
"datasets": [
|
||||
{
|
||||
"path": "tatsu-lab/alpaca",
|
||||
"type": "alpaca",
|
||||
},
|
||||
],
|
||||
"num_epochs": 1,
|
||||
"max_steps": 15,
|
||||
"micro_batch_size": 4,
|
||||
"gradient_accumulation_steps": 4,
|
||||
"output_dir": temp_dir,
|
||||
"learning_rate": 0.00001,
|
||||
"optimizer": "adamw_torch",
|
||||
"lr_scheduler": "cosine",
|
||||
"flash_attention": True,
|
||||
"deepspeed": "deepspeed_configs/zero3_bf16_cpuoffload_all.json",
|
||||
}
|
||||
)
|
||||
|
||||
# write cfg to yaml file
|
||||
Path(temp_dir).mkdir(parents=True, exist_ok=True)
|
||||
with open(Path(temp_dir) / "config.yaml", "w", encoding="utf-8") as fout:
|
||||
fout.write(yaml.dump(cfg.to_dict(), Dumper=yaml.Dumper))
|
||||
|
||||
execute_subprocess_async(
|
||||
[
|
||||
"accelerate",
|
||||
"launch",
|
||||
"--num-processes",
|
||||
"2",
|
||||
"-m",
|
||||
"axolotl.cli.train",
|
||||
str(Path(temp_dir) / "config.yaml"),
|
||||
]
|
||||
)
|
||||
|
||||
@@ -66,8 +66,6 @@ class TestFAXentropyLlama(unittest.TestCase):
|
||||
},
|
||||
],
|
||||
"num_epochs": 1,
|
||||
"max_steps": 10,
|
||||
"save_steps": 10,
|
||||
"micro_batch_size": 8,
|
||||
"gradient_accumulation_steps": 1,
|
||||
"output_dir": temp_dir,
|
||||
|
||||
@@ -56,8 +56,6 @@ class TestLoraLlama(unittest.TestCase):
|
||||
},
|
||||
],
|
||||
"num_epochs": 2,
|
||||
"max_steps": 20,
|
||||
"save_steps": 10,
|
||||
"micro_batch_size": 8,
|
||||
"gradient_accumulation_steps": 1,
|
||||
"output_dir": temp_dir,
|
||||
@@ -111,7 +109,6 @@ class TestLoraLlama(unittest.TestCase):
|
||||
},
|
||||
],
|
||||
"num_epochs": 2,
|
||||
"max_steps": 20,
|
||||
"save_steps": 0.5,
|
||||
"micro_batch_size": 8,
|
||||
"gradient_accumulation_steps": 1,
|
||||
|
||||
@@ -113,7 +113,7 @@ class TestCustomOptimizers(unittest.TestCase):
|
||||
def test_fft_schedule_free_adamw(self, temp_dir):
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "HuggingFaceTB/SmolLM2-135M",
|
||||
"base_model": "HuggingFaceTB/SmolLM-135M",
|
||||
"sequence_len": 1024,
|
||||
"val_set_size": 0.1,
|
||||
"special_tokens": {
|
||||
|
||||
@@ -31,7 +31,7 @@ class TestPackedLlama(unittest.TestCase):
|
||||
# pylint: disable=duplicate-code
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "HuggingFaceTB/SmolLM2-135M",
|
||||
"base_model": "HuggingFaceTB/SmolLM-135M",
|
||||
"sequence_len": 1024,
|
||||
"sample_packing": True,
|
||||
"flash_attention": True,
|
||||
|
||||
Reference in New Issue
Block a user