Commit graph

1,534 commits

Author SHA1 Message Date
Daniel Han
fe3c84d250 Update rl.py 2025-02-19 21:41:17 -08:00
Daniel Han
4dfbbb2b9a Update rl.py 2025-02-19 17:58:25 -08:00
Daniel Han
90158637d3 Update rl.py 2025-02-19 16:40:37 -08:00
Daniel Han
5129cf3049 Update rl.py 2025-02-19 16:38:44 -08:00
Daniel Han
98ad241821 Update rl.py 2025-02-19 16:37:12 -08:00
Daniel Han
09d8c9b2ca Update rl.py 2025-02-19 12:51:22 -08:00
Daniel Han
e06905724d Update rl.py 2025-02-19 12:47:15 -08:00
Daniel Han
dc04a82307 Update rl.py 2025-02-19 03:41:51 -08:00
Daniel Han
3797412198 Optional logits 2025-02-19 02:23:00 -08:00
Seth Weidman
c2938ccc83 Update rl_replacements.py (#1754)
Fix typo in comment: know -> now.

This was printed when running the Llama3.1_(8B)-GRPO.ipynb example notebook, so I'd expect others to run into it as well.
2025-02-19 02:12:07 -08:00
Daniel Han
b7a53c37bd Update rl_replacements.py 2025-02-18 01:57:18 -08:00
Daniel Han
9eb8e34a15 Update rl_replacements.py 2025-02-18 00:17:07 -08:00
Daniel Han
ab27ddc6a3 Update rl.py 2025-02-18 00:13:26 -08:00
Daniel Han
6148ce8d46 Update rl.py 2025-02-18 00:09:11 -08:00
Daniel Han
79141331f1 Update rl.py 2025-02-18 00:05:40 -08:00
Daniel Han
16f0cc2214 Update rl.py 2025-02-18 00:01:09 -08:00
Daniel Han
7a8ae1f272 Update rl.py 2025-02-17 23:57:57 -08:00
Daniel Han
2c81afe484 Update rl_replacements.py 2025-02-17 23:47:52 -08:00
Daniel Han
d6325aa94d Update rl_replacements.py 2025-02-17 22:30:20 -08:00
Daniel Han
6741b050d7 Update rl_replacements.py 2025-02-17 22:30:13 -08:00
Daniel Han
99b56e4193 Update rl.py 2025-02-17 22:24:57 -08:00
Daniel Han
6688732d2e unsloth_num_chunks 2025-02-17 22:17:11 -08:00
Daniel Han
cc523685ae Update rl_replacements.py 2025-02-17 21:17:58 -08:00
Daniel Han
df9c98bc14 Update rl_replacements.py 2025-02-17 21:10:26 -08:00
Daniel Han
afb60b7772 Update rl_replacements.py 2025-02-17 21:08:32 -08:00
Daniel Han
cb8a2a5550 Update rl_replacements.py 2025-02-17 21:03:44 -08:00
Daniel Han
bd3bd2103d Update rl_replacements.py 2025-02-17 20:38:18 -08:00
Daniel Han
b6f473b804 Update rl_replacements.py 2025-02-17 20:21:20 -08:00
Daniel Han
d05e13c70c Update rl.py 2025-02-17 20:08:15 -08:00
Daniel Han
c9b15eb00f Update rl.py 2025-02-17 20:04:26 -08:00
Daniel Han
d5002e1ebf Update rl_replacements.py 2025-02-17 20:04:14 -08:00
Daniel Han
798f8daaf1 Update rl.py 2025-02-17 20:00:04 -08:00
Daniel Han
c2917b06c7 Update rl.py 2025-02-17 19:58:17 -08:00
Daniel Han
53e14f4b2d Update rl_replacements.py 2025-02-17 19:53:49 -08:00
Daniel Han
fe483b6210 Update rl_replacements.py 2025-02-17 19:45:07 -08:00
Daniel Han
86512dd59f Update rl_replacements.py 2025-02-17 19:44:43 -08:00
Daniel Han
74f9c9e1fd Update llama.py 2025-02-17 19:16:41 -08:00
Daniel Han
397a0e49d5 Update llama.py 2025-02-17 00:49:35 -08:00
Daniel Han
f68ab5ad84 Update rl_replacements.py 2025-02-17 00:43:11 -08:00
Daniel Han
518ecd6638 Update rl_replacements.py 2025-02-17 00:05:32 -08:00
Daniel Han
da456076d3 Update rl_replacements.py 2025-02-16 23:49:20 -08:00
Daniel Han
759d23c7a4 Update llama.py 2025-02-16 21:22:35 -08:00
Daniel Han
74463e92d9 Update rl_replacements.py 2025-02-16 21:06:47 -08:00
Daniel Han
d4e9e38dfe Update rl_replacements.py 2025-02-16 20:55:26 -08:00
Daniel Han
f665fb243d Update rl_replacements.py 2025-02-16 20:55:11 -08:00
Daniel Han
834d3d69a1 Update rl_replacements.py 2025-02-16 20:20:01 -08:00
Daniel Han
3db0f8a0b3 Update rl_replacements.py 2025-02-16 19:47:39 -08:00
Daniel Han
ccc609fa43 Update rl_replacements.py 2025-02-16 18:34:45 -08:00
Daniel Han
0174dfc14f Update rl_replacements.py 2025-02-16 18:27:04 -08:00
Daniel Han
bdf52260d4 Update rl_replacements.py 2025-02-16 18:09:03 -08:00