DoubleMathew cc29dc5c35 only warn about prepare causal attention mask when transformers<=4.52.4 (#2867)		2025-07-04 01:54:27 -07:00
..
__init__.py	vLLM Windows CUDA support [tested] (#2158)	2025-05-12 05:33:42 -07:00
_utils.py	fix quantized model parameter count method (#2855)	2025-07-01 23:36:59 -07:00
cohere.py	Fix renaming on other model than Llama (#2762)	2025-06-18 13:38:36 -07:00
dpo.py	Update dpo.py	2025-02-13 14:59:42 -08:00
falcon_h1.py	import undefined transformers_version for falcon model (#2822)	2025-06-28 17:41:19 -07:00
gemma.py	Fix renaming on other model than Llama (#2762)	2025-06-18 13:38:36 -07:00
gemma2.py	Fix renaming on other model than Llama (#2762)	2025-06-18 13:38:36 -07:00
granite.py	Fix renaming on other model than Llama (#2762)	2025-06-18 13:38:36 -07:00
llama.py	only warn about prepare causal attention mask when transformers<=4.52.4 (#2867)	2025-07-04 01:54:27 -07:00
llama4.py	Qwen 3	2025-05-02 03:09:44 -07:00
loader.py	Update CSM for faster inference (no compile) (#2865)	2025-07-02 16:59:56 -07:00
loader_utils.py	Update loader_utils.py	2025-05-12 21:06:30 -07:00
mapper.py	Gemma 3N (#2809)	2025-06-26 09:14:28 -07:00
mistral.py	Fix renaming on other model than Llama (#2762)	2025-06-18 13:38:36 -07:00
qwen2.py	Fix renaming on other model than Llama (#2762)	2025-06-18 13:38:36 -07:00
qwen3.py	Fix renaming on other model than Llama (#2762)	2025-06-18 13:38:36 -07:00
qwen3_moe.py	Fix renaming on other model than Llama (#2762)	2025-06-18 13:38:36 -07:00
rl.py	Fix GRPO (#2787)	2025-06-22 05:54:29 -07:00
rl_replacements.py	Bug fixes (#2805)	2025-06-26 02:17:12 -07:00
vision.py	Fix Gemma 3N (#2854)	2025-07-01 07:01:31 -07:00