unsloth/unsloth/models
2025-09-03 19:11:53 -07:00
..
__init__.py silienty skip falcon h1 import is transformers_version < 4.53.0 (#2912) 2025-07-09 14:05:41 -07:00
_utils.py Versioning 2025-08-28 03:19:14 -07:00
cohere.py Handle transformers move to dtype from torch_dtype (#3225) 2025-08-28 02:43:41 -07:00
dpo.py Update dpo.py 2025-02-13 14:59:42 -08:00
falcon_h1.py Merge pull request #3224 from DefiWimar7/typos 2025-08-28 02:46:27 -07:00
gemma.py Merge pull request #3224 from DefiWimar7/typos 2025-08-28 02:46:27 -07:00
gemma2.py Handle transformers move to dtype from torch_dtype (#3225) 2025-08-28 02:43:41 -07:00
granite.py Handle transformers move to dtype from torch_dtype (#3225) 2025-08-28 02:43:41 -07:00
llama.py Update llama.py 2025-09-03 19:11:53 -07:00
llama4.py Qwen 3 2025-05-02 03:09:44 -07:00
loader.py GPT OSS Bug fixes (#3231) 2025-08-28 09:39:46 -07:00
loader_utils.py Update loader_utils.py 2025-05-12 21:06:30 -07:00
mapper.py Nightly (#3169) 2025-08-15 05:03:38 -07:00
mistral.py Update mistral.py, showed flag to not call cut cross entropy (#3233) 2025-08-29 01:32:21 -07:00
qwen2.py Fix renaming on other model than Llama (#2762) 2025-06-18 13:38:36 -07:00
qwen3.py fix is casual for qwen3 (#3213) 2025-08-26 04:45:20 -07:00
qwen3_moe.py Fix renaming on other model than Llama (#2762) 2025-06-18 13:38:36 -07:00
rl.py GPT OSS Bug fixes (#3231) 2025-08-28 09:39:46 -07:00
rl_replacements.py get_per_token_logps_and_entropies: return tuple instead of dict (#3080) 2025-08-02 03:31:41 -07:00
vision.py Handle transformers move to dtype from torch_dtype (#3225) 2025-08-28 02:43:41 -07:00