20 Commits (dca27b4412e8e41cadcd623582222e1c216db78b)
 

Author SHA1 Message Date
hiyouga dca27b4412 add logits processor 2 years ago
hiyouga ed6161fa6a remove unused code 2 years ago
hiyouga 72a85ccc39 add wechat 2 years ago
hiyouga b8a034807e tiny fix 2 years ago
hiyouga e3aaef7d4a fix layer norm name in PPO 2 years ago
hiyouga bd565af370 fix #1 2 years ago
hiyouga 50d9a20f81 alter rewards data type 2 years ago
hiyouga e6126244c1 fix possibly OOM error 2 years ago
hiyouga fd709eacff fix bug at inference 2 years ago
hiyouga 38ca429228 update readme 2 years ago
hiyouga 740a5daf56 support BLOOM models 2 years ago
hiyouga a72492e649 remove dummy code 2 years ago
hiyouga 6ccdfb4001 update readme 2 years ago
hiyouga 7698f9aa9a update readme 2 years ago
hiyouga 8ff96509fa add pre-training script 2 years ago
hiyouga c0e5df92d6 fix checkpoint loading 2 years ago
hiyouga ce71cc8b6d tiny fix 2 years ago
hiyouga 166c837b95 tiny fix 2 years ago
hiyouga 0c9fda01e3 use fp16 model, add logcallback 2 years ago
hiyouga 769c6ab56b Initial commit 2 years ago