ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
unsloth/unsloth/models
History
Datta Nimmaturi c8ed5e5037
 Do not force set beta to 0 for DAPO (#3604)
2025-11-16 22:39:36 -08:00
..
__init__.py Formatting & bug fixes (#3563) 2025-11-07 06:00:22 -08:00
_utils.py fix qwen3 vl gradient accumulation (#3598) 2025-11-15 02:26:34 -08:00
cohere.py Formatting & bug fixes (#3563) 2025-11-07 06:00:22 -08:00
dpo.py Formatting & bug fixes (#3563) 2025-11-07 06:00:22 -08:00
falcon_h1.py Fix: prevent rope_embedding AssertionError by checking kv_seq_len before reuse (#3578) 2025-11-14 03:06:33 -08:00
gemma.py Formatting & bug fixes (#3563) 2025-11-07 06:00:22 -08:00
gemma2.py Formatting & bug fixes (#3563) 2025-11-07 06:00:22 -08:00
granite.py Formatting & bug fixes (#3563) 2025-11-07 06:00:22 -08:00
llama.py fix qwen3 vl gradient accumulation (#3598) 2025-11-15 02:26:34 -08:00
llama4.py Qwen 3 2025-05-02 03:09:44 -07:00
loader.py Support for out-of-source quantizers (#3534) 2025-11-14 02:52:24 -08:00
loader_utils.py Formatting & bug fixes (#3563) 2025-11-07 06:00:22 -08:00
mapper.py Formatting & bug fixes (#3563) 2025-11-07 06:00:22 -08:00
mistral.py Formatting & bug fixes (#3563) 2025-11-07 06:00:22 -08:00
qwen2.py Formatting & bug fixes (#3563) 2025-11-07 06:00:22 -08:00
qwen3.py Fix: prevent rope_embedding AssertionError by checking kv_seq_len before reuse (#3578) 2025-11-14 03:06:33 -08:00
qwen3_moe.py Formatting & bug fixes (#3563) 2025-11-07 06:00:22 -08:00
rl.py Do not force set beta to 0 for DAPO (#3604) 2025-11-16 22:39:36 -08:00
rl_replacements.py Formatting & bug fixes (#3563) 2025-11-07 06:00:22 -08:00
vision.py add trust_remote_code kwarg (#3564) 2025-11-07 14:16:35 -08:00