Commit graph

1,366 commits

Author SHA1 Message Date
Daniel Han
ff3375ee8e autocast 2025-02-12 03:50:07 -08:00
Daniel Han
5d628d9397 Update llama.py 2025-02-12 03:32:12 -08:00
Daniel Han
f1f8e52e2d Update llama.py 2025-02-12 03:24:32 -08:00
Daniel Han
07d89f2264 Update llama.py 2025-02-12 03:08:40 -08:00
Daniel Han
648fd043c9 Update llama.py 2025-02-12 03:03:43 -08:00
Daniel Han
9878a74d89 Update rl.py 2025-02-12 02:27:34 -08:00
Daniel Han
e2240d4e4f Update rl_replacements.py 2025-02-12 01:53:16 -08:00
Daniel Han
23ba1ca3ac Update rl_replacements.py 2025-02-11 23:58:26 -08:00
Daniel Han
1a3e53e166 Update rl.py 2025-02-11 23:47:33 -08:00
Daniel Han
6706504b94 Update loader_utils.py 2025-02-11 23:45:26 -08:00
Daniel Han
4bc009df1a Update _utils.py 2025-02-11 23:10:11 -08:00
Daniel Han
c643d950f7 Update rl_replacements.py 2025-02-11 22:02:41 -08:00
Daniel Han
5465fdf65f Update llama.py 2025-02-11 22:02:22 -08:00
Daniel Han
a292b02934 Update rl_replacements.py 2025-02-11 22:00:44 -08:00
Daniel Han
07c1e4a4d2 Merge branch 'main' into nightly 2025-02-11 21:31:34 -08:00
Daniel Han
ecd969d402 Update rl_replacements.py 2025-02-11 21:31:23 -08:00
Daniel Han
98687fa2ae Update rl_replacements.py 2025-02-11 21:18:55 -08:00
Daniel Han
89ffa609d4 Update rl_replacements.py 2025-02-11 21:16:56 -08:00
Daniel Han
bbb6d1589d Update rl_replacements.py 2025-02-11 21:14:41 -08:00
Daniel Han
4185a04c2e Update rl_replacements.py 2025-02-11 21:13:31 -08:00
Daniel Han
005d3cea8a extra RL replacements 2025-02-11 21:10:32 -08:00
Daniel Han
e5d7fe6725 Update rl.py 2025-02-11 20:39:55 -08:00
Daniel Han
997d102011 Update rl_replacements.py 2025-02-11 20:37:18 -08:00
Daniel Han
4be051e52c Extra replacements 2025-02-11 20:35:34 -08:00
Daniel Han
f764c75b1f Update rl.py 2025-02-11 19:34:41 -08:00
Daniel Han
362de80ea5 Update rl.py 2025-02-11 19:34:29 -08:00
Daniel Han
8bab4a5eec Update rl.py 2025-02-11 19:00:53 -08:00
Daniel Han
791c6fc04f Update rl.py 2025-02-11 18:57:35 -08:00
Daniel Han
91395f46bd Update rl.py 2025-02-11 18:56:09 -08:00
Daniel Han
910db6badf Update rl.py 2025-02-11 18:54:39 -08:00
Daniel Han
cf3bde0da8 Update rl.py 2025-02-11 18:49:09 -08:00
Daniel Han
013152891d NEFTune 2025-02-11 18:19:16 -08:00
Daniel Han
538f852bd0 Update rl.py 2025-02-11 16:20:14 -08:00
Daniel Han
4ecc4c3500 Update rl.py 2025-02-11 16:04:56 -08:00
Daniel Han
a5016481c5 Update rl.py 2025-02-11 16:03:33 -08:00
Daniel Han
1e78f1bb80 Update rl.py 2025-02-11 15:57:32 -08:00
Daniel Han
fb443fcfd6 Update rl.py 2025-02-11 15:53:46 -08:00
Daniel Han
eaed3eb015 Patching 2025-02-11 15:11:16 -08:00
Daniel Han
4be70adb57 Update rl.py 2025-02-11 15:00:44 -08:00
Daniel Han
65439f81c5 Update rl.py 2025-02-11 14:27:31 -08:00
Daniel Han
9d94c475ad max seq length 2025-02-11 14:22:19 -08:00
Daniel Han
7a6b9b8459 Update rl.py 2025-02-11 14:11:33 -08:00
Daniel Han
5fa88c3cb9 Update rl.py 2025-02-11 03:25:37 -08:00
Daniel Han
657ce5cab9 Update rl.py 2025-02-11 03:23:05 -08:00
Daniel Han
5c07343168 Update tokenizer_utils.py 2025-02-11 03:21:59 -08:00
Daniel Han
0d99380d54 Update rl.py 2025-02-11 03:20:41 -08:00
Daniel Han
af03bfc047 Update rl.py 2025-02-11 03:16:07 -08:00
Daniel Han
58c0823fc9 Update rl.py 2025-02-11 03:08:04 -08:00
Daniel Han
6697a6d95b Update rl.py 2025-02-11 03:05:44 -08:00
Daniel Han
71aff2d7f9 Update rl.py 2025-02-11 03:04:05 -08:00