ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
1,827 commits 391 branches 58 tags 304 MiB
Commit graph

1,827 commits

This branch
This branch
All branches
Author SHA1 Message Date
Daniel Han
2b9f86bec8 Update vision.py 2025-03-14 07:09:23 -07:00
Daniel Han
962c470ef7 Merge branch 'main' into nightly 2025-03-14 07:09:16 -07:00
Daniel Han
8cd65ba494 Gemma 3, bug fixes (#2014) 
* 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

* Update vision.py

* Temporary patches

* Update loader.py

* model names

* Gemma 3 chat template

* Bug fixes

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update llama.py

* Update llama.py

* Update rl.py

* Update chat_templates.py

* Update chat_templates.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update loader.py

* Update vision.py

* Update vision.py

* Revert

* Update _utils.py

* forced precision

* Autocast

* Update vision.py

* Update vision.py

* Update rl.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update rl.py

* vLLM fixes

* constexpr

* Update vision.py

* Update vision.py

* Update vision.py

* Update rl.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

* Update _utils.py

* Update _utils.py

* Update _utils.py

* Update save.py

* New models

* Triton windows update (#1976)

* Update pyproject.toml

* Update README.md

* Update RMS LayerNorm implementation, and list compr. change in chat templates (#1974)

* Update RMS LayerNorm implementation with optimizations and testing suite

* perf: optimize list comprehension in get_ollama_eos_tokens

* Update Zoo

* Update llama.py

* Update llama.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update rl_replacements.py

* Update vision.py

* grpo fix

* Update rl_replacements.py

* Update vision.py

* Update rl_replacements.py

* Update vision.py

* Update mapper.py

* Update vision.py

* Update vision.py

* Update loader.py

---------

Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in>
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>
Co-authored-by: Akshay Behl <126911424+Captain-T2004@users.noreply.github.com>
 2025-03-14 06:42:44 -07:00
Daniel Han
935cb93b1a Update loader.py 2025-03-14 06:26:01 -07:00
Daniel Han
f89f30aa24 Update vision.py 2025-03-14 06:17:35 -07:00
Daniel Han
0a74e08557 Update vision.py 2025-03-14 06:17:20 -07:00
Daniel Han
376e0d25ce Update mapper.py 2025-03-14 06:15:44 -07:00
Daniel Han
0642665ea5 Update vision.py 2025-03-14 06:11:51 -07:00
Daniel Han
22eeee212d Update rl_replacements.py 2025-03-14 06:11:19 -07:00
Daniel Han
571f3abe54 Update vision.py 2025-03-14 06:06:10 -07:00
Daniel Han
d3439f887e Update rl_replacements.py 2025-03-14 06:01:42 -07:00
Daniel Han
e6e071a456 grpo fix 2025-03-14 05:57:17 -07:00
Daniel Han
4ca856fefd Update vision.py 2025-03-14 05:54:57 -07:00
Daniel Han
5b24b2e761 Update rl_replacements.py 2025-03-14 05:51:08 -07:00
Daniel Han
c524050481 Update vision.py 2025-03-14 05:41:17 -07:00
Daniel Han
3baed67682 Update vision.py 2025-03-14 05:40:56 -07:00
Daniel Han
27e3809815 Update vision.py 2025-03-14 04:59:29 -07:00
Daniel Han
2a6fb83630 Update vision.py 2025-03-14 04:58:32 -07:00
Daniel Han
658f23f3f6 Update vision.py 2025-03-14 04:51:43 -07:00
Daniel Han
d2b8043b79 Update vision.py 2025-03-14 04:43:11 -07:00
Daniel Han
d7173b482d Update vision.py 2025-03-14 04:40:29 -07:00
Daniel Han
dbccfd7ad9 Update vision.py 2025-03-14 04:39:00 -07:00
Daniel Han
86ef8913ce Update vision.py 2025-03-14 04:37:31 -07:00
Daniel Han
d64d082499 Update vision.py 2025-03-14 04:30:26 -07:00
Daniel Han
c217844c4c Update vision.py 2025-03-14 04:30:02 -07:00
Daniel Han
f21ad4b1e4 Update vision.py 2025-03-14 04:26:10 -07:00
Daniel Han
4eb0a29add Update llama.py 2025-03-14 04:08:17 -07:00
Daniel Han
cb06d8576c Update llama.py 2025-03-14 04:02:41 -07:00
Daniel Han
052b8e2a0d Merge branch 'main' into nightly 2025-03-14 02:59:25 -07:00
Daniel Han
65d24536fd Merge branch 'nightly' of https://github.com/unslothai/unsloth into nightly 2025-03-14 02:54:47 -07:00
Daniel Han
8950086aed Update Zoo 2025-03-14 02:54:40 -07:00
Nino Risteski
e339b41266 Update RMS LayerNorm implementation, and list compr. change in chat templates (#1974) 
* Update RMS LayerNorm implementation with optimizations and testing suite

* perf: optimize list comprehension in get_ollama_eos_tokens
 2025-03-14 02:53:21 -07:00
Akshay Behl
4ce91f3888 Triton windows update (#1976) 
* Update pyproject.toml

* Update README.md
 2025-03-14 02:51:30 -07:00
Daniel Han
360e799f5d New models 2025-03-14 02:41:52 -07:00
Daniel Han
7429c5698c Update save.py 2025-03-14 02:32:53 -07:00
Daniel Han
ce516fc814 Update _utils.py 2025-03-14 02:21:15 -07:00
Daniel Han
be2a5cf3a6 Update _utils.py 2025-03-14 02:07:13 -07:00
Daniel Han
9a5d455dac Update _utils.py 2025-03-14 02:00:03 -07:00
Daniel Han
2881726516 Update _utils.py 2025-03-14 01:44:04 -07:00
Daniel Han
59ce585627 Update llama.py 2025-03-14 01:39:45 -07:00
Daniel Han
538a5df0de Update llama.py 2025-03-14 01:36:12 -07:00
Daniel Han
c3b0716b69 Update llama.py 2025-03-14 01:26:45 -07:00
Daniel Han
382a8aef2a Update llama.py 2025-03-14 01:25:35 -07:00
Daniel Han
e913cd4bb5 Update llama.py 2025-03-14 01:20:18 -07:00
Daniel Han
24a79c14d2 Update llama.py 2025-03-14 01:18:54 -07:00
Daniel Han
96e3269dd8 Update llama.py 2025-03-14 01:18:04 -07:00
Daniel Han
0d5c76a37f Update llama.py 2025-03-14 00:16:24 -07:00
Daniel Han
d2ce827244 Update rl.py 2025-03-13 23:08:46 -07:00
Daniel Han
86a59d5fd9 Update vision.py 2025-03-13 18:34:26 -07:00
Daniel Han
3614c2c271 Update vision.py 2025-03-13 18:31:03 -07:00