ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
1,127 commits 391 branches 58 tags 304 MiB
Commit graph

1,127 commits

This branch
This branch
All branches
Author SHA1 Message Date
Daniel Han
0a646e40f5 Big bug fixes 
Fixes:
1. #1932
2. #1931
3. #1928
4. #1925
5. #1921
6. #1918
7. #1923
8. #1922
9. #1921

Please do: `pip install --upgrade --force-reinstall --no-deps unsloth unsloth_zoo` for local machines. Colab / Kaggle please restart and delete / disconnect runtime and redo

Apologies on the issues!
 2025-03-06 14:43:48 -08:00
Daniel Han
53d0ba079e Bug fixes (#1920) 
* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update pyproject.toml

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update _utils.py

* Update llama.py

* Update _utils.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* GRPO optimized

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Selective Log softmax

* Fix GRPO bsz

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Fix TRL

* Metrics GRPO

* Update rl_replacements.py

* Update rl_replacements.py

* No compile

* Update rl.py

* Remove docs

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* llama-quantize on WINDOWS WSL error fix - edit save.py (gguf saving breaks) (#1649)

* edit save.py to fix gguf saving breaks.

* add check for .exe or not exe file extension for linux and windows

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* unsloth_num_chunks

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py (#1754)

Fix typo in comment: know -> now.

This was printed when running the Llama3.1_(8B)-GRPO.ipynb example notebook, so I'd expect others to run into it as well.

* Optional logits

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* fix an import error (#1767)

* fix an import error

* Delete .gitignore

* Update loader.py

* Update save.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>

* SamplingParams

* Convert mask to float (#1762)

* [Windows Support] Add latest `xformers` wheels to pyproject.toml (#1753)

* Add latest xformers

* Add a couple of lines to docs

* vLLMSamplingParams

* Update __init__.py

* default num_chunks == -1

* Versioning

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update _utils.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update pyproject.toml

* Update pyproject.toml

* Export Model to ollama.com  (#1648)

* Ollama Export Model to ollama.com

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* Check for model_name

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* subprocess use instead of requests | added check for ollama server

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* create_ollama_model

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* create_ollama_model | fix

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* Push to Ollama

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

---------

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* Update cross_entropy_loss.py

* torch_cuda_device

* Update utils.py

* Update utils.py

* Update utils.py

* device

* device

* Update loader.py

* Update llama.py

* Update README.md

* Update llama.py

* Update llama.py

* Update _utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* __version__

* Update rl.py

* Bug fixes

* Bug fixes

* Update llama.py

* Update _utils.py

* _wrap_fast_inference

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update _utils.py

* SFT dataset prepare

* Update pyproject.toml

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update utils.py

* bug fix

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update __init__.py

* Update _utils.py

* Update _utils.py

* Update _utils.py

* Update _utils.py

* Update _utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update _utils.py

* Update __init__.py

* Update _utils.py

* Version

* versioning

* Update _utils.py

* Update llama.py

* Update llama.py

---------

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>
Co-authored-by: Gennadii Manzhos <105049664+everythingisc00l@users.noreply.github.com>
Co-authored-by: Seth Weidman <seth@sethweidman.com>
Co-authored-by: Nino Risteski <95188570+NinoRisteski@users.noreply.github.com>
Co-authored-by: Edd <68678137+Erland366@users.noreply.github.com>
Co-authored-by: Ben <6579034+versipellis@users.noreply.github.com>
Co-authored-by: Jyotin Goel <120490013+gjyotin305@users.noreply.github.com>
 2025-03-06 05:16:15 -08:00
Daniel Han
83eaa2f087 Logits fixes (#1916) 
* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update pyproject.toml

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update _utils.py

* Update llama.py

* Update _utils.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* GRPO optimized

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Selective Log softmax

* Fix GRPO bsz

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Fix TRL

* Metrics GRPO

* Update rl_replacements.py

* Update rl_replacements.py

* No compile

* Update rl.py

* Remove docs

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* llama-quantize on WINDOWS WSL error fix - edit save.py (gguf saving breaks) (#1649)

* edit save.py to fix gguf saving breaks.

* add check for .exe or not exe file extension for linux and windows

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* unsloth_num_chunks

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py (#1754)

Fix typo in comment: know -> now.

This was printed when running the Llama3.1_(8B)-GRPO.ipynb example notebook, so I'd expect others to run into it as well.

* Optional logits

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* fix an import error (#1767)

* fix an import error

* Delete .gitignore

* Update loader.py

* Update save.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>

* SamplingParams

* Convert mask to float (#1762)

* [Windows Support] Add latest `xformers` wheels to pyproject.toml (#1753)

* Add latest xformers

* Add a couple of lines to docs

* vLLMSamplingParams

* Update __init__.py

* default num_chunks == -1

* Versioning

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update _utils.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update pyproject.toml

* Update pyproject.toml

* Export Model to ollama.com  (#1648)

* Ollama Export Model to ollama.com

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* Check for model_name

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* subprocess use instead of requests | added check for ollama server

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* create_ollama_model

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* create_ollama_model | fix

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* Push to Ollama

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

---------

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* Update cross_entropy_loss.py

* torch_cuda_device

* Update utils.py

* Update utils.py

* Update utils.py

* device

* device

* Update loader.py

* Update llama.py

* Update README.md

* Update llama.py

* Update llama.py

* Update _utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* __version__

* Update rl.py

* Bug fixes

* Bug fixes

* Update llama.py

* Update _utils.py

* _wrap_fast_inference

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update _utils.py

* SFT dataset prepare

* Update pyproject.toml

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update utils.py

* bug fix

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update __init__.py

* Update _utils.py

* Update _utils.py

* Update _utils.py

* Update _utils.py

* Update _utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update _utils.py

* Update __init__.py

* Update _utils.py

* Version

---------

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>
Co-authored-by: Gennadii Manzhos <105049664+everythingisc00l@users.noreply.github.com>
Co-authored-by: Seth Weidman <seth@sethweidman.com>
Co-authored-by: Nino Risteski <95188570+NinoRisteski@users.noreply.github.com>
Co-authored-by: Edd <68678137+Erland366@users.noreply.github.com>
Co-authored-by: Ben <6579034+versipellis@users.noreply.github.com>
Co-authored-by: Jyotin Goel <120490013+gjyotin305@users.noreply.github.com>
 2025-03-06 02:32:32 -08:00
Daniel Han
303daeb1e1 Python 3.12 fix 2025-03-05 12:58:24 -08:00
Daniel Han
2afeb37839 Many bug fixes (#1900) 
* Update rl.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* autocast

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update pyproject.toml

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update _utils.py

* Update llama.py

* Update _utils.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* GRPO optimized

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Selective Log softmax

* Fix GRPO bsz

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Fix TRL

* Metrics GRPO

* Update rl_replacements.py

* Update rl_replacements.py

* No compile

* Update rl.py

* Remove docs

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* llama-quantize on WINDOWS WSL error fix - edit save.py (gguf saving breaks) (#1649)

* edit save.py to fix gguf saving breaks.

* add check for .exe or not exe file extension for linux and windows

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* unsloth_num_chunks

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py (#1754)

Fix typo in comment: know -> now.

This was printed when running the Llama3.1_(8B)-GRPO.ipynb example notebook, so I'd expect others to run into it as well.

* Optional logits

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* fix an import error (#1767)

* fix an import error

* Delete .gitignore

* Update loader.py

* Update save.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>

* SamplingParams

* Convert mask to float (#1762)

* [Windows Support] Add latest `xformers` wheels to pyproject.toml (#1753)

* Add latest xformers

* Add a couple of lines to docs

* vLLMSamplingParams

* Update __init__.py

* default num_chunks == -1

* Versioning

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update _utils.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update pyproject.toml

* Update pyproject.toml

* Export Model to ollama.com  (#1648)

* Ollama Export Model to ollama.com

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* Check for model_name

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* subprocess use instead of requests | added check for ollama server

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* create_ollama_model

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* create_ollama_model | fix

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* Push to Ollama

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

---------

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* Update cross_entropy_loss.py

* torch_cuda_device

* Update utils.py

* Update utils.py

* Update utils.py

* device

* device

* Update loader.py

* Update llama.py

* Update README.md

* Update llama.py

* Update llama.py

* Update _utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* __version__

* Update rl.py

* Bug fixes

* Bug fixes

* Update llama.py

* Update _utils.py

* _wrap_fast_inference

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update _utils.py

* SFT dataset prepare

* Update pyproject.toml

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update utils.py

* bug fix

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update __init__.py

---------

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>
Co-authored-by: Gennadii Manzhos <105049664+everythingisc00l@users.noreply.github.com>
Co-authored-by: Seth Weidman <seth@sethweidman.com>
Co-authored-by: Nino Risteski <95188570+NinoRisteski@users.noreply.github.com>
Co-authored-by: Edd <68678137+Erland366@users.noreply.github.com>
Co-authored-by: Ben <6579034+versipellis@users.noreply.github.com>
Co-authored-by: Jyotin Goel <120490013+gjyotin305@users.noreply.github.com>
 2025-03-05 05:13:32 -08:00
Daniel Han
6208d99833 Bug fix 2025-03-04 13:26:47 -08:00
Daniel Han
c813f2de1d Bug fix 2025-03-04 04:22:23 -08:00
Daniel Han
d5c427adea Bug fix 2025-03-04 04:12:38 -08:00
Daniel Han
3e5f061133 Bug fixes (#1891) 
* Update rl.py

* Patching

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* NEFTune

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Extra replacements

* Update rl_replacements.py

* Update rl.py

* extra RL replacements

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update _utils.py

* Update loader_utils.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* autocast

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update pyproject.toml

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update _utils.py

* Update llama.py

* Update _utils.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* GRPO optimized

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Selective Log softmax

* Fix GRPO bsz

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Fix TRL

* Metrics GRPO

* Update rl_replacements.py

* Update rl_replacements.py

* No compile

* Update rl.py

* Remove docs

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* llama-quantize on WINDOWS WSL error fix - edit save.py (gguf saving breaks) (#1649)

* edit save.py to fix gguf saving breaks.

* add check for .exe or not exe file extension for linux and windows

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* unsloth_num_chunks

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py (#1754)

Fix typo in comment: know -> now.

This was printed when running the Llama3.1_(8B)-GRPO.ipynb example notebook, so I'd expect others to run into it as well.

* Optional logits

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* fix an import error (#1767)

* fix an import error

* Delete .gitignore

* Update loader.py

* Update save.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>

* SamplingParams

* Convert mask to float (#1762)

* [Windows Support] Add latest `xformers` wheels to pyproject.toml (#1753)

* Add latest xformers

* Add a couple of lines to docs

* vLLMSamplingParams

* Update __init__.py

* default num_chunks == -1

* Versioning

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update _utils.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update pyproject.toml

* Update pyproject.toml

* Export Model to ollama.com  (#1648)

* Ollama Export Model to ollama.com

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* Check for model_name

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* subprocess use instead of requests | added check for ollama server

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* create_ollama_model

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* create_ollama_model | fix

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* Push to Ollama

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

---------

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>

* Update cross_entropy_loss.py

* torch_cuda_device

* Update utils.py

* Update utils.py

* Update utils.py

* device

* device

* Update loader.py

* Update llama.py

* Update README.md

* Update llama.py

* Update llama.py

* Update _utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* __version__

* Update rl.py

* Bug fixes

---------

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>
Co-authored-by: Gennadii Manzhos <105049664+everythingisc00l@users.noreply.github.com>
Co-authored-by: Seth Weidman <seth@sethweidman.com>
Co-authored-by: Nino Risteski <95188570+NinoRisteski@users.noreply.github.com>
Co-authored-by: Edd <68678137+Erland366@users.noreply.github.com>
Co-authored-by: Ben <6579034+versipellis@users.noreply.github.com>
Co-authored-by: Jyotin Goel <120490013+gjyotin305@users.noreply.github.com>
 2025-03-04 03:55:49 -08:00
Michael Han
6491abfb78 Merge pull request #1885 from unslothai/shimmyshimmer-patch-6 
Update README.md
 2025-03-03 21:28:00 -08:00
Michael Han
c018ea28db Update README.md 2025-03-03 21:27:20 -08:00
Michael Han
e02561d883 Update README.md 2025-03-02 20:44:26 -08:00
Michael Han
8b5883275d Update README.md 2025-03-02 20:35:27 -08:00
Michael Han
788563f8fe Update README.md 2025-03-02 20:34:36 -08:00
J. M Areeb Uzair
c6d2433547 Added Python version warning to Windows Install Section (#1872) 
I spent half a day on the wrong Python version, so I am adding this big, red sign.
 2025-03-02 03:48:21 -08:00
Mohamed Mekkouri
8180e9803c Fix Layernorm when num_cols not a power of 2 (#1867) 
* fix

* Update layernorm.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>
 2025-03-01 14:23:22 -08:00
Daniel Han
8a72e20aa5 Update vision.py 2025-03-01 13:47:01 -08:00
Daniel Han
4f166026d7 LoRA 2025-03-01 02:52:20 -08:00
Daniel Han
481e3e41b2 Update llama.py 2025-03-01 00:23:20 -08:00
Daniel Han
f4748c020d Update _utils.py 2025-03-01 00:21:28 -08:00
Daniel Han
f3b5469213 Update granite.py 2025-03-01 00:20:34 -08:00
Daniel Han
6b735edbcb Update granite.py 2025-03-01 00:19:12 -08:00
Daniel Han
6485cbb499 Prelim release 2025-03-01 00:13:11 -08:00
Aditya Ghai
08bc291300 Direct windows support for unsloth (#1841) 
* Direct Windows Support(main)

* Update pyproject.toml

* Update README.md

Added the suggested changes to README
 2025-02-27 20:25:46 -08:00
Daniel Han
841626c405 Update rl_replacements.py 2025-02-27 03:46:47 -08:00
Daniel Han
f55395b5f0 Update rl_replacements.py 2025-02-27 03:42:03 -08:00
Michael Han
569b4422c4 Update README.md 2025-02-26 17:03:47 -08:00
Michael Han
86aea0b4f8 Update README.md 2025-02-26 16:58:32 -08:00
Kareem
71d2a24575 fixed syntax warnings (#1522) 
* fixed most of syntax warnings

* all syntaxwarnings fixed

* Syntax fixes

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>
 2025-02-26 03:50:37 -08:00
Charles London
96346a5f35 Fix key error in GRPOTrainer (#1818) 
* fix keyerror in GRPOTrainer

* check for train in _metrics
 2025-02-25 15:22:35 -08:00
Igor Kilbas
455517aae9 Fix: GRPO with Mistral and importing (#1831) 
* fix: mistral and importing

* minor change

* Style :)

* Update mistral.py

* Update mistral.py

* Update mistral.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>
 2025-02-25 15:21:26 -08:00
Michael Han
ab701257d6 Update README.md 2025-02-21 22:59:19 -08:00
Daniel Han
734a9a0611 Update _utils.py 2025-02-20 09:24:07 -08:00
Daniel Han
4570c8b41e Bug Fixes (#1774) 
* Update rl.py

* Update tokenizer_utils.py

* Auto patching

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update rl.py

* Update tokenizer_utils.py

* Update rl.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update tokenizer_utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* max seq length

* Update rl.py

* Update rl.py

* Patching

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* NEFTune

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Extra replacements

* Update rl_replacements.py

* Update rl.py

* extra RL replacements

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update _utils.py

* Update loader_utils.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* autocast

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update pyproject.toml

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update _utils.py

* Update llama.py

* Update _utils.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* GRPO optimized

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Selective Log softmax

* Fix GRPO bsz

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Fix TRL

* Metrics GRPO

* Update rl_replacements.py

* Update rl_replacements.py

* No compile

* Update rl.py

* Remove docs

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* llama-quantize on WINDOWS WSL error fix - edit save.py (gguf saving breaks) (#1649)

* edit save.py to fix gguf saving breaks.

* add check for .exe or not exe file extension for linux and windows

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* unsloth_num_chunks

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py (#1754)

Fix typo in comment: know -> now.

This was printed when running the Llama3.1_(8B)-GRPO.ipynb example notebook, so I'd expect others to run into it as well.

* Optional logits

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* fix an import error (#1767)

* fix an import error

* Delete .gitignore

* Update loader.py

* Update save.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>

* SamplingParams

* Convert mask to float (#1762)

* [Windows Support] Add latest `xformers` wheels to pyproject.toml (#1753)

* Add latest xformers

* Add a couple of lines to docs

* vLLMSamplingParams

* Update __init__.py

* default num_chunks == -1

* Versioning

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update _utils.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update pyproject.toml

* Update pyproject.toml

---------

Co-authored-by: Gennadii Manzhos <105049664+everythingisc00l@users.noreply.github.com>
Co-authored-by: Seth Weidman <seth@sethweidman.com>
Co-authored-by: Nino Risteski <95188570+NinoRisteski@users.noreply.github.com>
Co-authored-by: Edd <68678137+Erland366@users.noreply.github.com>
Co-authored-by: Ben <6579034+versipellis@users.noreply.github.com>
 2025-02-20 09:20:49 -08:00
Daniel Han
cd3a733602 bug fix 2025-02-20 04:47:12 -08:00
Daniel Han
a45a08f91b Memory Efficient GRPO (#1773) 
* Update __init__.py

* Update loader.py

* Update rl.py

* Update rl.py

* Update _utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Better TRL handling

* Update rl.py

* Update tokenizer_utils.py

* Auto patching

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update rl.py

* Update tokenizer_utils.py

* Update rl.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update tokenizer_utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* max seq length

* Update rl.py

* Update rl.py

* Patching

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* NEFTune

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Extra replacements

* Update rl_replacements.py

* Update rl.py

* extra RL replacements

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update _utils.py

* Update loader_utils.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* autocast

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update pyproject.toml

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update _utils.py

* Update llama.py

* Update _utils.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* GRPO optimized

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Selective Log softmax

* Fix GRPO bsz

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Fix TRL

* Metrics GRPO

* Update rl_replacements.py

* Update rl_replacements.py

* No compile

* Update rl.py

* Remove docs

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* llama-quantize on WINDOWS WSL error fix - edit save.py (gguf saving breaks) (#1649)

* edit save.py to fix gguf saving breaks.

* add check for .exe or not exe file extension for linux and windows

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* unsloth_num_chunks

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py (#1754)

Fix typo in comment: know -> now.

This was printed when running the Llama3.1_(8B)-GRPO.ipynb example notebook, so I'd expect others to run into it as well.

* Optional logits

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* fix an import error (#1767)

* fix an import error

* Delete .gitignore

* Update loader.py

* Update save.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>

* SamplingParams

* Convert mask to float (#1762)

* [Windows Support] Add latest `xformers` wheels to pyproject.toml (#1753)

* Add latest xformers

* Add a couple of lines to docs

* vLLMSamplingParams

* Update __init__.py

* default num_chunks == -1

* Versioning

---------

Co-authored-by: Gennadii Manzhos <105049664+everythingisc00l@users.noreply.github.com>
Co-authored-by: Seth Weidman <seth@sethweidman.com>
Co-authored-by: Nino Risteski <95188570+NinoRisteski@users.noreply.github.com>
Co-authored-by: Edd <68678137+Erland366@users.noreply.github.com>
Co-authored-by: Ben <6579034+versipellis@users.noreply.github.com>
 2025-02-20 04:23:28 -08:00
Daniel Han
fbe9ee80d4 Update README.md (#1768) 2025-02-19 23:24:05 -08:00
Daniel Han
66a1345421 Fix weird tokenizer issue 2025-02-15 03:12:43 -08:00
Daniel Han
895c7ca320 Update mapper.py 2025-02-15 02:48:36 -08:00
Daniel Han
c5e9299a73 Add GRPO metrics (#1718) 
* Update llama.py

* Update llama.py

* Faster inference?

* Update llama.py

* Update llama.py

* Update utils.py

* Update llama.py

* Update llama.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update mapper.py

* Fast Inference via vLLM

* Update llama.py

* Update llama.py

* Update utils.py

* Create rl.py

* PatchRL

* Update rl.py

* Update rl.py

* Update rl.py

* PatchRLStatistics

* Update rl.py

* Update rl.py

* Update rl.py

* Update utils.py

* Update utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* RL metrics

* Update rl.py

* RL metrics

* Update __init__.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update chat_templates.py

* Update mapper.py

* Fp8 cache

* Update llama.py

* Update llama.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update __init__.py

* Update loader.py

* Update rl.py

* Update rl.py

* Update _utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Better TRL handling

* Update rl.py

* Update tokenizer_utils.py

* Auto patching

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update rl.py

* Update tokenizer_utils.py

* Update rl.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update tokenizer_utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* max seq length

* Update rl.py

* Update rl.py

* Patching

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* NEFTune

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Extra replacements

* Update rl_replacements.py

* Update rl.py

* extra RL replacements

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update _utils.py

* Update loader_utils.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* autocast

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update pyproject.toml

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update _utils.py

* Update llama.py

* Update _utils.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* GRPO optimized

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Selective Log softmax

* Fix GRPO bsz

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Fix TRL

* Metrics GRPO

* Update rl_replacements.py

* Update rl_replacements.py
 2025-02-15 02:24:01 -08:00
Daniel Han
c66350a48a Memory efficient GRPO, DPO etc (#1716) 
* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Faster inference?

* Update llama.py

* Update llama.py

* Update utils.py

* Update llama.py

* Update llama.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update mapper.py

* Fast Inference via vLLM

* Update llama.py

* Update llama.py

* Update utils.py

* Create rl.py

* PatchRL

* Update rl.py

* Update rl.py

* Update rl.py

* PatchRLStatistics

* Update rl.py

* Update rl.py

* Update rl.py

* Update utils.py

* Update utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* RL metrics

* Update rl.py

* RL metrics

* Update __init__.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update chat_templates.py

* Update mapper.py

* Fp8 cache

* Update llama.py

* Update llama.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update __init__.py

* Update loader.py

* Update rl.py

* Update rl.py

* Update _utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Better TRL handling

* Update rl.py

* Update tokenizer_utils.py

* Auto patching

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update rl.py

* Update tokenizer_utils.py

* Update rl.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update tokenizer_utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* max seq length

* Update rl.py

* Update rl.py

* Patching

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* NEFTune

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Extra replacements

* Update rl_replacements.py

* Update rl.py

* extra RL replacements

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update _utils.py

* Update loader_utils.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* autocast

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update pyproject.toml

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update _utils.py

* Update llama.py

* Update _utils.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* GRPO optimized

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Selective Log softmax

* Fix GRPO bsz

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Fix TRL
 2025-02-15 01:19:39 -08:00
Daniel Han
3136fd9611 Fix bugs (#1706) 
* Bug fixes

* fix: flash_attn_detection_error (#1556)

* fix: flash_attn_detection_error

* Update _utils.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>

* Update mapper.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* dim fix

* Update _utils.py

* Torch 2.6 support

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Faster inference?

* Update llama.py

* Update llama.py

* Update utils.py

* Update llama.py

* Update llama.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update mapper.py

* Fast Inference via vLLM

* Update llama.py

* Update llama.py

* Update utils.py

* Create rl.py

* PatchRL

* Update rl.py

* Update rl.py

* Update rl.py

* PatchRLStatistics

* Update rl.py

* Update rl.py

* Update rl.py

* Update utils.py

* Update utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* RL metrics

* Update rl.py

* RL metrics

* Update __init__.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update chat_templates.py

* Update mapper.py

* Fp8 cache

* Update llama.py

* Update llama.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update __init__.py

* Update loader.py

* Update rl.py

* Update rl.py

* Update _utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Better TRL handling

* Update rl.py

* Update tokenizer_utils.py

* Auto patching

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update rl.py

* Update tokenizer_utils.py

* Update rl.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update tokenizer_utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* max seq length

* Update rl.py

* Update rl.py

* Patching

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* NEFTune

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Extra replacements

* Update rl_replacements.py

* Update rl.py

* extra RL replacements

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update _utils.py

* Update loader_utils.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* autocast

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update pyproject.toml

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update _utils.py

* Update llama.py

* Update _utils.py

* Update rl_replacements.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

---------

Co-authored-by: Zhe Zhang <2631992879@qq.com>
 2025-02-13 19:12:19 -08:00
Daniel Han
4f9301d321 Update _utils.py 2025-02-13 15:14:17 -08:00
Daniel Han
26f8d8580b Update pyproject.toml 2025-02-13 15:13:55 -08:00
Daniel Han
39eaefce14 Update rl.py 2025-02-13 15:02:50 -08:00
Daniel Han
635e921506 Update _utils.py 2025-02-13 14:59:52 -08:00
Daniel Han
5c19724e7f Update dpo.py 2025-02-13 14:59:42 -08:00
Daniel Han
43cda3240c Update __init__.py 2025-02-13 14:55:14 -08:00
Daniel Han
010de17c90 Update _utils.py 2025-02-13 14:54:49 -08:00
Daniel Han
95fb1d699d Fix bugs (#1701) 
* Phi 4

* Update llama.py

* Torch.Cuda Is Available Condition and Warning (#1545)

* check for torch.cuda and triton if available
on my machine(mac m3) the cuda were not available

* Update pyproject.toml

* Update __init__.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>

* Update mistral.py

* Update mistral.py

* Update _utils.py

* Update _utils.py

* Update _utils.py

* Update _utils.py

* Update _utils.py

* Fix

* Bug fixes

* Update mapper.py

* Add dropout to granite to match HF's implementation (#1557)

Signed-off-by: datta0 <venkatadattasainimmaturi@gmail.com>

* Update llama.py

* Update llama.py

* Bug fixes

* fix: flash_attn_detection_error (#1556)

* fix: flash_attn_detection_error

* Update _utils.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>

* Update mapper.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* Update gemma.py

* dim fix

* Update _utils.py

* Torch 2.6 support

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Faster inference?

* Update llama.py

* Update llama.py

* Update utils.py

* Update llama.py

* Update llama.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update utils.py

* Update mapper.py

* Fast Inference via vLLM

* Update llama.py

* Update llama.py

* Update utils.py

* Create rl.py

* PatchRL

* Update rl.py

* Update rl.py

* Update rl.py

* PatchRLStatistics

* Update rl.py

* Update rl.py

* Update rl.py

* Update utils.py

* Update utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* RL metrics

* Update rl.py

* RL metrics

* Update __init__.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update chat_templates.py

* Update mapper.py

* Fp8 cache

* Update llama.py

* Update llama.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update __init__.py

* Update loader.py

* Update rl.py

* Update rl.py

* Update _utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Better TRL handling

* Update rl.py

* Update tokenizer_utils.py

* Auto patching

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update rl.py

* Update tokenizer_utils.py

* Update rl.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update tokenizer_utils.py

* Update rl.py

* Update rl.py

* Update rl.py

* max seq length

* Update rl.py

* Update rl.py

* Patching

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* NEFTune

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Extra replacements

* Update rl_replacements.py

* Update rl.py

* extra RL replacements

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update _utils.py

* Update loader_utils.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* autocast

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update pyproject.toml

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update llama.py

* Update _utils.py

---------

Signed-off-by: datta0 <venkatadattasainimmaturi@gmail.com>
Co-authored-by: AminWhat <88392440+aminwhat@users.noreply.github.com>
Co-authored-by: Datta Nimmaturi <datta.nimmaturi@nutanix.com>
Co-authored-by: Zhe Zhang <2631992879@qq.com>
 2025-02-13 14:50:44 -08:00