ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
1,806 commits 391 branches 58 tags 304 MiB
Commit graph

1,806 commits

This branch
This branch
All branches
Author SHA1 Message Date
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
Daniel Han
4644fd8dac Update vision.py 2025-03-13 18:26:30 -07:00
Daniel Han
33ba26211a constexpr 2025-03-13 18:23:29 -07:00
Daniel Han
3accb89df6 vLLM fixes 2025-03-13 17:57:46 -07:00
Daniel Han
7c0f3f73e9 Update rl.py 2025-03-13 16:02:56 -07:00
Daniel Han
904f405adf Gemma 3 bug fixes (#2005) 
* 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

* 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

---------

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>
 2025-03-13 06:41:42 -07:00
Daniel Han
cb0d41e30e Update vision.py 2025-03-13 06:39:17 -07:00
Daniel Han
6c02f36051 Update vision.py 2025-03-13 06:34:55 -07:00
Daniel Han
14b37cc5f4 Update vision.py 2025-03-13 06:25:18 -07:00
Daniel Han
5bb6090140 Update vision.py 2025-03-13 06:24:37 -07:00
Daniel Han
7b60d1d32d Update vision.py 2025-03-13 06:15:42 -07:00
Daniel Han
32cc8ad0d3 Update rl.py 2025-03-13 06:12:36 -07:00
Daniel Han
23875a899a Update vision.py 2025-03-13 06:08:33 -07:00
Daniel Han
f45bddbdae Update vision.py 2025-03-13 06:06:24 -07:00
Daniel Han
0288db2fa7 Autocast 2025-03-13 06:02:33 -07:00
Daniel Han
33c7219dc7 forced precision 2025-03-13 05:46:02 -07:00
Daniel Han
ac5f2b33dc Update _utils.py 2025-03-13 05:38:21 -07:00
Daniel Han
9f89844a81 Revert 2025-03-13 05:13:17 -07:00
Daniel Han
885265db8d Update vision.py 2025-03-13 01:30:06 -07:00
Daniel Han
ba096eda6e Update vision.py 2025-03-13 01:27:50 -07:00
Daniel Han
7bd582a6ff Update loader.py 2025-03-13 01:17:48 -07:00
Daniel Han
4a917c3a92 Update vision.py 2025-03-13 01:15:25 -07:00