ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
1,748 commits 391 branches 58 tags 304 MiB
Commit graph

1,748 commits

This branch
This branch
All branches
Author SHA1 Message Date
Daniel Han
79b59cc8a6 Update vision.py 2025-03-12 21:35:29 -07:00
Daniel Han
702f85bd54 Update vision.py 2025-03-12 21:34:34 -07:00
Daniel Han
eaa5947342 Update vision.py 2025-03-12 21:33:22 -07:00
Daniel Han
f904e66e7b Update vision.py 2025-03-12 21:31:37 -07:00
Daniel Han
be660d3bb1 Bug fixes 2025-03-12 21:30:02 -07:00
Daniel Han
7fe2874157 Gemma 3 chat template 2025-03-12 20:37:19 -07:00
Daniel Han
5349526e35 model names 2025-03-12 20:04:27 -07:00
Daniel Han
fa6628b3e9 Update loader.py 2025-03-12 19:25:41 -07:00
Daniel Han
914bd92a8c Temporary patches 2025-03-12 19:20:17 -07:00
Daniel Han
8e9f52f16d Update vision.py 2025-03-12 06:51:23 -07:00
Daniel Han
f8a490e16e Merge branch 'main' into nightly 2025-03-12 05:00:45 -07:00
Daniel Han
33e020c064 Update _utils.py 2025-03-12 04:52:07 -07:00
Daniel Han
2c54bfd7ff Update _utils.py 2025-03-12 04:46:34 -07:00
Daniel Han
356a74d4dd Update mapper.py 2025-03-12 04:07:45 -07:00
Daniel Han
f35d5977d6 Gemma 3 (#1986) 
* 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

* Bug fixes

* FastModel

* __doc__

* Update vision.py

* Update loader.py

* Update loader.py

* Update loader.py

* version

* move use_modelscope to _utils (#1938)

* move use_modelscope to _utils

* Update _utils.py

* Update loader.py

---------

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

* Don't use revision when loading model_config and is_peft=True (#1949)

* More syntax warnings (#1944)

* move use_modelscope to _utils

* fix

* Update _utils.py

* Update loader.py

---------

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

* Update loader.py

* Full finetuning and other fixes

* UNSLOTH_ENABLE_FULL_FINETUNING

* Update loader.py

* Update loader.py

* Update loader.py

* Update vision.py

* Update vision.py

* full finetuning

* Update loader.py

* Update loader.py

* Update loader.py

* Update _utils.py

* max_seq_length

* Update rl.py

* Update rl.py

* Update rl.py

* Update pyproject.toml

* AutoModelForImageTextToText

* Update mapper.py

* Update pyproject.toml

* Update _utils.py

* Update _utils.py

* Update _utils.py

* Batch samples

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update _utils.py

* Update loader.py

* Update vision.py

* Update loader.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update mapper.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>
Co-authored-by: Kareem <81531392+KareemMusleh@users.noreply.github.com>
Co-authored-by: Wilson Wu <140025193+wiwu2390@users.noreply.github.com>
 2025-03-12 01:23:34 -07:00
Daniel Han
89a2517a8d Update mapper.py 2025-03-11 23:35:46 -07:00
Daniel Han
c319cacac4 Update vision.py 2025-03-11 22:55:34 -07:00
Daniel Han
a3c2856977 Update vision.py 2025-03-11 22:36:51 -07:00
Daniel Han
8148f3e7f0 Update vision.py 2025-03-11 22:34:57 -07:00
Daniel Han
7208177c66 Update loader.py 2025-03-11 22:31:14 -07:00
Daniel Han
d4e0f42951 Update vision.py 2025-03-11 22:29:06 -07:00
Daniel Han
7f03388c66 Update loader.py 2025-03-11 22:27:53 -07:00
Daniel Han
b061ab453e Update _utils.py 2025-03-11 22:22:36 -07:00
Daniel Han
032d109d98 Update loader.py 2025-03-11 22:02:39 -07:00
Daniel Han
7e76b42b46 Update loader.py 2025-03-11 20:45:53 -07:00
Daniel Han
50803b0a2f Update loader.py 2025-03-11 20:44:01 -07:00
Daniel Han
2249e266b7 Update loader.py 2025-03-11 20:43:25 -07:00
Daniel Han
904fe3485e Batch samples 2025-03-11 19:46:41 -07:00
Daniel Han
1b71f08854 Update _utils.py 2025-03-11 15:25:21 -07:00
Daniel Han
b7131a0697 Update _utils.py 2025-03-11 15:22:16 -07:00
Daniel Han
57c6894583 Update _utils.py 2025-03-11 15:20:20 -07:00
Daniel Han
361fa338d8 Update pyproject.toml 2025-03-11 14:59:29 -07:00
Daniel Han
683bd5fd9b Update mapper.py 2025-03-11 05:37:29 -07:00
Daniel Han
b78f12cff8 AutoModelForImageTextToText 2025-03-11 04:30:01 -07:00
Daniel Han
e680904d46 Update pyproject.toml 2025-03-11 00:18:55 -07:00
Daniel Han
a564d888bd Update rl.py 2025-03-10 05:00:45 -07:00
Daniel Han
2cedc89ac8 Update rl.py 2025-03-10 04:58:59 -07:00
Daniel Han
b97ac4e76f Update rl.py 2025-03-10 04:57:47 -07:00
Daniel Han
c6f73dd521 max_seq_length 2025-03-10 04:39:25 -07:00
Daniel Han
3443a8503f Update _utils.py 2025-03-10 00:31:49 -07:00
Daniel Han
c9dafd5eaf Update loader.py 2025-03-09 23:33:21 -07:00
Daniel Han
49dce011e9 Update loader.py 2025-03-09 23:24:21 -07:00
Daniel Han
5e23241d6e Update loader.py 2025-03-09 23:22:13 -07:00
Daniel Han
a6215fcc50 full finetuning 2025-03-09 23:18:52 -07:00
Daniel Han
2f737d1144 Update vision.py 2025-03-09 23:13:30 -07:00
Daniel Han
4560215e41 Update vision.py 2025-03-09 23:11:28 -07:00
Daniel Han
4122cc7547 Update loader.py 2025-03-09 23:08:34 -07:00
Daniel Han
4cf033f6c7 Update loader.py 2025-03-09 23:06:06 -07:00
Daniel Han
186a2f6ee6 Update loader.py 2025-03-09 23:03:27 -07:00
Daniel Han
d41e5578e1 UNSLOTH_ENABLE_FULL_FINETUNING 2025-03-09 22:57:24 -07:00