ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
2,423 commits 391 branches 58 tags 304 MiB
Commit graph

2,423 commits

This branch
This branch
All branches
Author SHA1 Message Date
Daniel Han
146aa01707 Update rl_replacements.py 2025-06-25 18:53:19 -07:00
Daniel Han
29e202fb4c Update rl_replacements.py 2025-06-25 18:51:54 -07:00
Daniel Han
07a6d7f773 Update rl_replacements.py 2025-06-25 18:50:45 -07:00
Daniel Han
6251c72e46 Merge branch 'main' into nightly 2025-06-25 16:50:18 -07:00
Daniel Han
7c0e4b15de Update llama.py 2025-06-25 02:09:56 -07:00
Daniel Han
9ac3754fcf Update llama.py 2025-06-25 01:57:15 -07:00
Daniel Han
8098b3d7b7 Debugging only 2025-06-25 01:44:07 -07:00
Michael Han
a5233a7937 Update README.md 
Updating links
 2025-06-25 01:32:24 -07:00
Daniel Han
f9ea2cb9f2 Merge branch 'main' into nightly 2025-06-24 02:03:47 -07:00
Lei Zhenyuan
cf3859b62a [3/N] Enable intel GPU for unsloth (#2620) 
* enable intel xpu changes within kernels

* reslove torch.version < 2.6

* change version check to 2.6.0

* resolve comments for torch_gpu_device

* resolve amp fwd comments

* fix typo

* change cuda default logic

* clean this pr

* add HAS_CUDA_STREAM as default False

* split GPU streams to cuda and xpu streams

* add optional
 2025-06-24 02:01:28 -07:00
Daniel Han
c267ad973d Merge branch 'main' of https://github.com/unslothai/unsloth into nightly 2025-06-24 01:36:03 -07:00
Daniel Han
b6f625a3a2 Merge branch 'main' into nightly 2025-06-24 01:36:02 -07:00
DoubleMathew
1b4ca535ae move min_sms in is_big_gpu inside DEVICE_TYPE if else (#2792) 
log is not defined in torch inductor so remove

Remove log.warning entirely
 2025-06-23 18:57:55 -07:00
pluesclues
1fc64a0a1b Fixed Sequence Classification errors, loaded model weirdly (#2793) 2025-06-23 18:56:56 -07:00
Michael Han
0da61b418e Update issue templates 2025-06-23 05:34:46 -07:00
Daniel Han
b3a8df0beb Update issue templates 2025-06-23 05:26:28 -07:00
Lei Zhenyuan
8846fbf1e8 [5/N] Enable intel GPU for unsloth (#2768) 
* add is_big_gpu support for xpu

* make code unsloth's style
 2025-06-23 04:47:34 -07:00
kilavvy
096a49fa81 Docs: Fix typo and improve MoE docstrings (#2784) 
* Update qwen3_moe.py

* Update interface.py
 2025-06-23 01:09:23 -07:00
Daniel Han
c81b1864be Fix GRPO (#2787) 
* Update _utils.py

* Update _utils.py

* versioning

* 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 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

* 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 vision.py

* HF Transfer

* fix(utils): add missing importlib import to fix NameError (#2134)

This commit fixes a NameError that occurs when `importlib` is referenced in _utils.py
without being imported, especially when UNSLOTH_USE_MODELSCOPE=1 is enabled.
By adding the missing import statement, the code will no longer throw a NameError.

* Add QLoRA Train and Merge16bit Test (#2130)

* add reference and unsloth lora merging tests

* add test / dataset printing to test scripts

* allow running tests from repo root

* add qlora test readme

* more readme edits

* ruff formatting

* additional readme comments

* forgot to add actual tests

* add apache license

* Update pyproject.toml

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update loader.py

* Update loader.py

* Revert

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Bug fix

* Update mapper.py

* check SDPA for Mistral 3, Pixtral

* Update vision.py

* Versioning

* Update rl_replacements.py

* Update README.md

* add model registry

* move hf hub utils to unsloth/utils

* refactor global model info dicts to dataclasses

* fix dataclass init

* fix llama registration

* remove deprecated key function

* start registry reog

* add llama vision

* quant types -> Enum

* remap literal quant types to QuantType Enum

* add llama model registration

* fix quant tag mapping

* add qwen2.5 models to registry

* add option to include original model in registry

* handle quant types per model size

* separate registration of base and instruct llama3.2

* add QwenQVQ to registry

* add gemma3 to registry

* add phi

* add deepseek v3

* add deepseek r1 base

* add deepseek r1 zero

* add deepseek distill llama

* add deepseek distill models

* remove redundant code when constructing model names

* add mistral small to registry

* rename model registration methods

* rename deepseek registration methods

* refactor naming for mistral and phi

* add global register models

* refactor model registration tests for new registry apis

* add model search method

* remove deprecated registration api

* add quant type test

* add registry readme

* make llama registration more specific

* clear registry when executing individual model registration file

* more registry readme updates

* Update _auto_install.py

* Llama4

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Synthetic data

* Update mapper.py

* Xet and Synthetic

* Update synthetic.py

* Update loader.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update pyproject.toml

* Delete .gitignore

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update _utils.py

* Update pyproject.toml

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update synthetic.py

* Update chat_templates.py

* Seasame force float16 / float32

* Fix Seasame

* Update loader.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update loader.py

* is_multimodal

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update vision.py

* Update vision.py

* Update vision.py

* UNSLOTH_DISABLE_STATIC_GENERATION

* Update vision.py

* Auto vision detection

* Sesame

* Whisper

* Update loader.py

* Update loader.py

* Update loader.py

* Update mapper.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update vision.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update loader.py

* Update _utils.py

* Update rl.py

* versioning

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* Update rl.py

* logging

* Update pyproject.toml

* Update rl.py

* versioning

* Update rl.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* Update rl.py

* Update rl_replacements.py

* Update rl_replacements.py

* logits / temperature

* Update rl_replacements.py

* Update pyproject.toml

* Update rl_replacements.py

* Update rl_replacements.py

---------

Co-authored-by: naliazheli <nalia0316@gmail.com>
Co-authored-by: jeromeku <jerome.ku@gmail.com>
Co-authored-by: Jack Shi Wei Lun <87535974+jackswl@users.noreply.github.com>
Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com>
 2025-06-22 05:54:29 -07:00
Daniel Han
114c91ed03 Update rl_replacements.py 2025-06-22 05:51:07 -07:00
Daniel Han
54761f44c7 Update rl_replacements.py 2025-06-22 05:34:52 -07:00
Daniel Han
9fe9bd5bc7 Update pyproject.toml 2025-06-22 05:33:57 -07:00
Daniel Han
19d36655f7 Update rl_replacements.py 2025-06-22 05:32:38 -07:00
Daniel Han
5a16891484 logits / temperature 2025-06-22 04:54:18 -07:00
Daniel Han
f8484e7a19 Update rl_replacements.py 2025-06-22 03:44:56 -07:00
Daniel Han
56c17900ca Update rl_replacements.py 2025-06-22 03:39:30 -07:00
Daniel Han
bc8af1191d Update rl.py 2025-06-22 03:29:20 -07:00
Daniel Han
edb70686d3 Update rl_replacements.py 2025-06-22 02:55:00 -07:00
Daniel Han
3fa2f1436a Update rl_replacements.py 2025-06-22 02:37:52 -07:00
Daniel Han
2cb0ebc47e Merge branch 'main' into nightly 2025-06-22 02:37:11 -07:00
Daniel Han
c340fa3ac8 Update rl.py 2025-06-21 23:29:08 -07:00
Daniel Han
b8a990cfe4 Fix bf16 = None 2025-06-21 22:50:29 -07:00
Daniel Han
fc15642f52 Update rl.py 2025-06-21 22:26:46 -07:00
Daniel Han
8ba4f3f808 Merge branch 'main' into nightly 2025-06-21 22:21:10 -07:00
Daniel Han
016b4bff34 Update _utils.py 2025-06-21 22:20:46 -07:00
Daniel Han
d00ebe5fe6 Update rl_replacements.py 2025-06-21 22:20:32 -07:00
Daniel Han
8aa0a2dc37 Fix DAPO, TRL 0.19.0 2025-06-21 22:14:21 -07:00
simpissa
3e75f21086 Fix for grpo_compute_loss_slow (#2702) 
* slice last logit

* move slicing
 2025-06-21 21:58:06 -07:00
Daniel Han
a9b70d94e4 Mistral Small 3.2 2025-06-21 06:44:14 -07:00
amrothemich
dab00ef9a6 Update pyproject.toml (#2778) 
Switched pyproject license to dictionary type
 2025-06-21 02:44:24 -07:00
Michael Han
09ae01fa91 Merge pull request #2780 from rolandtannous/fix/gemma3-grpo-self-llm 
Fix AttributeError in GRPO trainer for models without llm attribute
 2025-06-20 21:15:54 -07:00
Roland Tannous
17563176d9 Fix Gemma3ForCausalLm does not have attribute self.llm 2025-06-21 01:07:32 +00:00
Roland Tannous
4a70f8e880 Additional tests for unsloth-zoo PR#174 2025-06-21 00:22:00 +00:00
Daniel Han
7e7510daf6 Merge branch 'main' of https://github.com/unslothai/unsloth 2025-06-20 06:30:43 -07:00
Daniel Han
9fbb88479c Update pyproject.toml 2025-06-20 06:30:35 -07:00
marcandrelarochelle
35d37ea567 Fix TRL 1.8.2 (#2774) 
* Fix for TRL 1.8.2

Regex matching LLM initialization

* Update Regex
 2025-06-20 06:28:58 -07:00
Daniel Han
1c7a9f46dc Update __init__.py 2025-06-20 06:13:45 -07:00
Daniel Han
a1e12d4243 Fix bugs 2025-06-20 06:09:03 -07:00
Datta Nimmaturi
83f20be8ad Enable vLLM to share memory space (#2712) 
* vLLM sleep once generation is done

* Make enable_sleep_model configurable

* Make default to false

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

* Force standby under environment variable

---------

Signed-off-by: datta0 <venkatadattasainimmaturi@gmail.com>
 2025-06-19 04:04:14 -07:00
Edd
3a7cf48532 Fix renaming on other model than Llama (#2762) 2025-06-18 13:38:36 -07:00