stceum
|
9aa640f27b
|
Bug Fix: off is parsed as False in yaml file, changed to disabled to avoid this.
Former-commit-id: 3ed063f281
|
2024-06-24 20:39:31 +08:00 |
|
hiyouga
|
98abb5c900
|
remove dup template
Former-commit-id: db9a1912e3
|
2024-06-22 01:31:32 +08:00 |
|
hiyouga
|
ccc9a895a6
|
fix api
Former-commit-id: 3ce44dda99
|
2024-06-22 00:00:38 +08:00 |
|
hiyouga
|
0844750bb9
|
tiny fix
Former-commit-id: 8d4f5093cf
|
2024-06-20 22:56:05 +08:00 |
|
hiyouga
|
6ea4680334
|
improve llamaboard
Former-commit-id: f22d8f9ca4
|
2024-06-19 23:46:03 +08:00 |
|
hiyouga
|
029c343537
|
fix llamaboard abort
Former-commit-id: 3f84411b5d
|
2024-06-19 23:22:28 +08:00 |
|
hiyouga
|
030b4811c7
|
update patcher
Former-commit-id: 3b040e8e0f
|
2024-06-19 21:27:00 +08:00 |
|
hiyouga
|
80e9f8e000
|
set dev version
Former-commit-id: 42e69a3c63
|
2024-06-19 21:08:16 +08:00 |
|
hiyouga
|
9c1b04cd11
|
release v0.8.2
Former-commit-id: 71327ba85a
|
2024-06-19 20:42:09 +08:00 |
|
hiyouga
|
3d72b1a856
|
fix jinja template
Former-commit-id: 2b596fb55f
|
2024-06-19 20:03:50 +08:00 |
|
hiyouga
|
7735456561
|
fix templates
Former-commit-id: 4cff6a4ad5
|
2024-06-19 17:44:05 +08:00 |
|
hiyouga
|
c9557241f6
|
fix bug
Former-commit-id: 6d2bf216ac
|
2024-06-19 03:49:23 +08:00 |
|
hiyouga
|
e73a235a38
|
use prefix to replace force system
Former-commit-id: 4f22eae8f4
|
2024-06-19 03:39:52 +08:00 |
|
hiyouga
|
bccc852f76
|
fix tool formatter, allow parallel function #4362
Former-commit-id: cd75b1fe9d
|
2024-06-19 03:23:51 +08:00 |
|
hoshi-hiyouga
|
6db02615d4
|
Merge pull request #4173 from mMrBun/main
Implemented the tool_formatter and tool_extractor for glm4 and Qwen2 tool_format
Former-commit-id: c0ca42566c
|
2024-06-19 03:18:55 +08:00 |
|
hiyouga
|
e3bf22f61b
|
add deepseek coder v2 #4346
Former-commit-id: a233fbc258
|
2024-06-18 22:53:54 +08:00 |
|
hiyouga
|
5156114981
|
fix #4357
Former-commit-id: 4bd77d8563
|
2024-06-18 22:42:45 +08:00 |
|
hiyouga
|
15a5eb6647
|
fix #4335
Former-commit-id: c96264bc47
|
2024-06-18 22:08:56 +08:00 |
|
hiyouga
|
19bf21efba
|
lint
Former-commit-id: 24c160df3d
|
2024-06-17 22:35:56 +08:00 |
|
hiyouga
|
3d85217464
|
update chat engine #4335
Former-commit-id: 7857c0990b
|
2024-06-17 19:07:17 +08:00 |
|
hiyouga
|
7ef169ed39
|
fix #4326
Former-commit-id: e2665e71c7
|
2024-06-17 18:17:48 +08:00 |
|
hoshi-hiyouga
|
06bbc29614
|
Update parser.py
Former-commit-id: 29c1f31baa
|
2024-06-16 02:57:00 +08:00 |
|
hiyouga
|
ce4a27a5f7
|
fix tol
Former-commit-id: 46093b5786
|
2024-06-16 01:38:44 +08:00 |
|
hiyouga
|
f25b8626bf
|
support pissa
Former-commit-id: 8c1046d78a
|
2024-06-16 01:08:12 +08:00 |
|
hiyouga
|
c0c6b8075a
|
tiny fix
Former-commit-id: 38b6b0f52e
|
2024-06-16 01:06:41 +08:00 |
|
hiyouga
|
96b82ccd4d
|
use fixture
Former-commit-id: 80a9e6bf94
|
2024-06-15 20:06:17 +08:00 |
|
hiyouga
|
8053929b20
|
add tests
Former-commit-id: 1b834f50be
|
2024-06-15 19:51:20 +08:00 |
|
hiyouga
|
f0d6e63f55
|
add minicpm #4227
Former-commit-id: 572d8bbfdd
|
2024-06-15 17:58:52 +08:00 |
|
hiyouga
|
2946153cea
|
add license
Former-commit-id: d87108daa6
|
2024-06-15 17:54:33 +08:00 |
|
hiyouga
|
fcbfa70c19
|
disable DP
Former-commit-id: d519b4d76d
|
2024-06-15 04:57:19 +08:00 |
|
hiyouga
|
ba9aa7e2aa
|
fix #4292
Former-commit-id: 9092f963db
|
2024-06-15 04:47:13 +08:00 |
|
hiyouga
|
ab66ae8cd2
|
fix #4295
Former-commit-id: 78589cf90c
|
2024-06-15 04:34:55 +08:00 |
|
hiyouga
|
a3f4925c2c
|
add test cases
Former-commit-id: b27269bd2b
|
2024-06-15 04:05:54 +08:00 |
|
hiyouga
|
27777c8e68
|
add quant check in webui export tab
Former-commit-id: c94e6c9411
|
2024-06-13 03:19:18 +08:00 |
|
hiyouga
|
8fccaf20c5
|
fix #4221
Former-commit-id: 6baafd4eb3
|
2024-06-13 02:48:21 +08:00 |
|
hiyouga
|
81ed4d8abf
|
fix #4209
DeepSpeed ZeRO3 has inflight param error when calling model.eval()
Former-commit-id: cf9f2d6c42
|
2024-06-13 02:25:50 +08:00 |
|
hiyouga
|
833aa324c2
|
clean code
Former-commit-id: 2ed8270112
|
2024-06-13 01:58:16 +08:00 |
|
hoshi-hiyouga
|
7366647b43
|
Merge pull request #4246 from hzhaoy/adapt-vllm-v0.5.0
adapt vllm==0.5.0
Former-commit-id: 1f23f25226
|
2024-06-13 01:54:02 +08:00 |
|
hiyouga
|
99ce085415
|
fix lint
Former-commit-id: 713fde4259
|
2024-06-13 00:48:44 +08:00 |
|
hzhaoy
|
65f2ba3802
|
adapt vllm==0.5.0
Former-commit-id: 8fb6366ebe
|
2024-06-12 18:29:03 +08:00 |
|
hiyouga
|
f8497921fe
|
fix #4242
Former-commit-id: 577de2fa07
|
2024-06-12 16:50:11 +08:00 |
|
Arthur Kim
|
bebca6d01c
|
Support vllm==0.5.0
Former-commit-id: d65a3f7cb6
|
2024-06-12 16:49:12 +09:00 |
|
hoshi-hiyouga
|
fecb9c9a76
|
Merge pull request #4204 from dignfei/main
fixbug:llama3在增量预训练时应该使用<|end_of_text|>标识文本的结束
Former-commit-id: 9049aab911
|
2024-06-11 17:06:10 +08:00 |
|
hoshi-hiyouga
|
bf3de9bfe8
|
Update pretrain.py
Former-commit-id: 0c29233237
|
2024-06-11 17:02:14 +08:00 |
|
hiyouga
|
8c574eb3cb
|
fix deepspeed version
Former-commit-id: cca6f35108
|
2024-06-11 16:52:36 +08:00 |
|
d
|
da39715085
|
经过大量的增量预训练,进行对比试验,发现这个bug:llama3在预训练时使用的tokenizer.eos_toke是'<|end_of_text|>' ,这里在每条数据后面也得用这个,而不是'<|eot_id|>',否则很容易导致严重的性能下降
Former-commit-id: 6979f3f848
|
2024-06-11 16:23:40 +08:00 |
|
hiyouga
|
5834651c4a
|
fix #4198
Former-commit-id: 89f2bd8c8c
|
2024-06-11 15:38:38 +08:00 |
|
hiyouga
|
53de7f7cc3
|
tiny fix
Former-commit-id: 90e14a960d
|
2024-06-11 12:48:53 +08:00 |
|
hiyouga
|
e3baa5aa08
|
tiny fix
Former-commit-id: 3f24337a8a
|
2024-06-11 01:04:16 +08:00 |
|
hiyouga
|
d6632fefc9
|
set dev version
Former-commit-id: 91e62a098f
|
2024-06-11 00:50:53 +08:00 |
|