ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
1,648 commits 391 branches 58 tags 304 MiB
Commit graph

1,648 commits

This branch
This branch
All branches
Author SHA1 Message Date
Daniel Han
9cdc4dd16b Update llama.py 2025-03-05 03:30:13 -08:00
Daniel Han
d72d014a2c Update rl.py 2025-03-05 03:24:08 -08:00
Daniel Han
c2ddabcfd6 Update rl_replacements.py 2025-03-05 01:11:03 -08:00
Daniel Han
f34fec15e6 Update rl_replacements.py 2025-03-05 01:03:13 -08:00
Daniel Han
36e1bc35f0 Update rl_replacements.py 2025-03-05 01:00:01 -08:00
Daniel Han
c3c6de3fc0 Update pyproject.toml 2025-03-05 00:56:56 -08:00
Daniel Han
4b75179783 SFT dataset prepare 2025-03-05 00:51:10 -08:00
Daniel Han
5891fea628 Update _utils.py 2025-03-04 19:44:54 -08:00
Daniel Han
79146518b6 Update llama.py 2025-03-04 19:39:49 -08:00
Daniel Han
a38f316c67 Update llama.py 2025-03-04 19:20:38 -08:00
Daniel Han
b64c9fb348 Update llama.py 2025-03-04 19:19:12 -08:00
Daniel Han
cae865ab6d Update llama.py 2025-03-04 19:15:40 -08:00
Daniel Han
e2c04a2d79 Update llama.py 2025-03-04 19:11:54 -08:00
Daniel Han
e481db0c42 Update llama.py 2025-03-04 19:08:59 -08:00
Daniel Han
94c7a2eeb8 Update llama.py 2025-03-04 19:04:46 -08:00
Daniel Han
b2a5aff5f9 Update llama.py 2025-03-04 19:02:12 -08:00
Daniel Han
b1ed1ba03d Update llama.py 2025-03-04 18:59:55 -08:00
Daniel Han
44c00ed6a6 Update llama.py 2025-03-04 18:21:54 -08:00
Daniel Han
5af86c488d Update llama.py 2025-03-04 18:18:02 -08:00
Daniel Han
937226b025 _wrap_fast_inference 2025-03-04 18:15:45 -08:00
Daniel Han
65ff11d2e3 Update _utils.py 2025-03-04 16:30:57 -08:00
Daniel Han
d8daa9d2fc Update llama.py 2025-03-04 16:16:21 -08:00
Daniel Han
1dafd6af8c Merge branch 'main' into nightly 2025-03-04 14:20:27 -08:00
Daniel Han
3a01f482a7 Bug fixes 2025-03-04 14:19:56 -08:00
Daniel Han
56691d8d03 Bug fix 2025-03-04 13:26:47 -08:00
Daniel Han
1a844651af Bug fix 2025-03-04 04:22:23 -08:00
Daniel Han
f0ae89360f Bug fix 2025-03-04 04:12:38 -08:00
Daniel Han
7cef895be7 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
Daniel Han
bf542e9ef6 Bug fixes 2025-03-04 03:47:51 -08:00
Daniel Han
e4bc56a087 Update rl.py 2025-03-04 03:31:38 -08:00
Daniel Han
20482bf9d6 __version__ 2025-03-04 02:57:54 -08:00
Daniel Han
a722a5d25d Update utils.py 2025-03-04 02:38:44 -08:00
Daniel Han
8d07b0e64a Update utils.py 2025-03-04 02:37:09 -08:00
Daniel Han
5ee394758d Update utils.py 2025-03-04 02:35:19 -08:00
Daniel Han
bfa92159d0 Update utils.py 2025-03-04 02:28:35 -08:00
Daniel Han
e854df5509 Update llama.py 2025-03-03 23:59:11 -08:00
Daniel Han
9955ec9c93 Update llama.py 2025-03-03 23:58:58 -08:00
Daniel Han
2793018ea6 Update llama.py 2025-03-03 23:41:37 -08:00
Daniel Han
69044ce605 Update llama.py 2025-03-03 23:32:02 -08:00
Daniel Han
06e2d96b39 Update llama.py 2025-03-03 23:00:26 -08:00
Michael Han
c3f80d7cd7 Merge pull request #1885 from unslothai/shimmyshimmer-patch-6 
Update README.md
 2025-03-03 21:28:00 -08:00
Michael Han
c77238cb31 Update README.md 2025-03-03 21:27:20 -08:00
Daniel Han
2415050cac Update utils.py 2025-03-03 18:46:16 -08:00
Daniel Han
18ab316dd2 Update utils.py 2025-03-03 18:33:18 -08:00
Daniel Han
91231ab3e6 Update utils.py 2025-03-03 18:29:35 -08:00
Daniel Han
1570f4cfe6 Update utils.py 2025-03-03 17:27:59 -08:00
Daniel Han
189146e389 Update utils.py 2025-03-03 17:17:25 -08:00
Daniel Han
0eee505371 Update _utils.py 2025-03-03 17:12:56 -08:00
Daniel Han
f40d5812f8 Update llama.py 2025-03-03 15:49:04 -08:00
Daniel Han
cc4c71d8cf Update llama.py 2025-03-03 15:48:55 -08:00