hiyouga
|
95a6f1759b
|
tiny fix
Former-commit-id: eac9921e5c
|
2023-06-04 12:55:40 +08:00 |
|
hiyouga
|
4d4636c48e
|
support QLoRA
Former-commit-id: 3b9eee8cd2
|
2023-06-04 00:08:56 +08:00 |
|
hiyouga
|
08d6079140
|
fix int8 inference
Former-commit-id: 1bd13d7ca1
|
2023-06-03 23:22:05 +08:00 |
|
hiyouga
|
3bf4b20d0b
|
reduce repetition penalty
Former-commit-id: 926291940d
|
2023-06-03 21:57:39 +08:00 |
|
hiyouga
|
4200d5d558
|
fix int8 inference
Former-commit-id: 0f69a0c19e
|
2023-06-03 21:17:47 +08:00 |
|
hiyouga
|
342ee89d28
|
add ziya prompt template
Former-commit-id: de09ee1315
|
2023-06-03 19:05:51 +08:00 |
|
hiyouga
|
c7d71dd8af
|
use low_cpu_mem_usage to speed up loading
Former-commit-id: 771f454ff1
|
2023-06-03 18:19:01 +08:00 |
|
hiyouga
|
42c9c8de39
|
add logits processor
Former-commit-id: dca27b4412
|
2023-06-03 16:34:54 +08:00 |
|
hiyouga
|
1392242958
|
remove unused code
Former-commit-id: ed6161fa6a
|
2023-06-03 00:10:54 +08:00 |
|
hiyouga
|
0f6efcc77a
|
add wechat
Former-commit-id: 72a85ccc39
|
2023-06-02 21:47:10 +08:00 |
|
hiyouga
|
36790c4e32
|
tiny fix
Former-commit-id: b8a034807e
|
2023-06-02 19:02:25 +08:00 |
|
hiyouga
|
6ab22a0181
|
fix layer norm name in PPO
Former-commit-id: e3aaef7d4a
|
2023-06-02 17:30:01 +08:00 |
|
hiyouga
|
b0e9a673be
|
fix #1
Former-commit-id: bd565af370
|
2023-06-02 14:25:00 +08:00 |
|
hiyouga
|
4003ddcc3b
|
alter rewards data type
Former-commit-id: 50d9a20f81
|
2023-06-02 14:19:51 +08:00 |
|
hiyouga
|
7e1be4c21a
|
fix possibly OOM error
Former-commit-id: e6126244c1
|
2023-06-01 23:54:44 +08:00 |
|
hiyouga
|
3f3b475412
|
fix bug at inference
Former-commit-id: fd709eacff
|
2023-05-31 18:11:53 +08:00 |
|
hiyouga
|
79011936c9
|
update readme
Former-commit-id: 38ca429228
|
2023-05-31 16:57:43 +08:00 |
|
hiyouga
|
3bfb086399
|
support BLOOM models
Former-commit-id: 740a5daf56
|
2023-05-31 16:54:06 +08:00 |
|
hoshi-hiyouga
|
1a5eacc98a
|
Merge pull request #1 from mMrBun/main
Support conversation via API.
Former-commit-id: c36620ece4
|
2023-05-30 16:34:00 +08:00 |
|
hiyouga
|
ddb456bbcb
|
remove dummy code
Former-commit-id: a72492e649
|
2023-05-30 16:28:00 +08:00 |
|
mMrBun
|
bc2e530e16
|
Support conversation via API.
Former-commit-id: 748b804bac
|
2023-05-30 15:00:28 +08:00 |
|
mMrBun
|
21ef968922
|
Support conversation via API.
Former-commit-id: e821682430
|
2023-05-30 14:46:22 +08:00 |
|
hiyouga
|
6ba162ef6c
|
update readme
Former-commit-id: 6ccdfb4001
|
2023-05-29 21:54:01 +08:00 |
|
hiyouga
|
e6a1469467
|
update readme
Former-commit-id: 7698f9aa9a
|
2023-05-29 21:53:02 +08:00 |
|
hiyouga
|
4c7c96e656
|
add pre-training script
Former-commit-id: 8ff96509fa
|
2023-05-29 21:37:22 +08:00 |
|
hiyouga
|
0ab4419b86
|
fix checkpoint loading
Former-commit-id: c0e5df92d6
|
2023-05-29 17:43:16 +08:00 |
|
hiyouga
|
03338163c2
|
tiny fix
Former-commit-id: ce71cc8b6d
|
2023-05-29 09:42:29 +08:00 |
|
hiyouga
|
b1517e7a0e
|
tiny fix
Former-commit-id: 166c837b95
|
2023-05-28 21:48:33 +08:00 |
|
hiyouga
|
87ba09e035
|
use fp16 model, add logcallback
Former-commit-id: 0c9fda01e3
|
2023-05-28 21:30:28 +08:00 |
|
hiyouga
|
54b8ce7b63
|
Initial commit
Former-commit-id: 769c6ab56b
|
2023-05-28 18:09:04 +08:00 |
|