247 Commits

Author SHA1 Message Date
hiyouga
9c1b04cd11 release v0.8.2
Former-commit-id: 71327ba85a3a1bb2d2d20c86951c6c7c0ba98829
2024-06-19 20:42:09 +08:00
hiyouga
3d72b1a856 fix jinja template
Former-commit-id: 2b596fb55ff689d2e488d9a9bbab98f70f356c3c
2024-06-19 20:03:50 +08:00
hiyouga
7735456561 fix templates
Former-commit-id: 4cff6a4ad55b24bf57db6be5cf817180c1ea5626
2024-06-19 17:44:05 +08:00
Jonery
c779899f7b Cleaner integration.
Former-commit-id: 5c2ff1b749a265dd3c979189ec491d8ac911a6f6
2024-06-19 12:29:40 +08:00
hiyouga
c9557241f6 fix bug
Former-commit-id: 6d2bf216ac3a48450e861148ce664dad717fd019
2024-06-19 03:49:23 +08:00
hiyouga
e73a235a38 use prefix to replace force system
Former-commit-id: 4f22eae8f405de918237d406e5e9847592925565
2024-06-19 03:39:52 +08:00
hiyouga
bccc852f76 fix tool formatter, allow parallel function #4362
Former-commit-id: cd75b1fe9d91fb52a9ae6de7435302ff06b4d933
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: c0ca42566c6aeccd8d384377510690eafef10995
2024-06-19 03:18:55 +08:00
hiyouga
e3bf22f61b add deepseek coder v2 #4346
Former-commit-id: a233fbc258d38c62d78b9d1eaf034720361795e6
2024-06-18 22:53:54 +08:00
hiyouga
5156114981 fix #4357
Former-commit-id: 4bd77d8563aa85230af65caf901214247e214bed
2024-06-18 22:42:45 +08:00
hiyouga
15a5eb6647 fix #4335
Former-commit-id: c96264bc477d65276557e9059cac7c550c4835a8
2024-06-18 22:08:56 +08:00
Jonery
c2734108e7 fix typo
Former-commit-id: 8f7c78b64138602406af748b0e15948ebbd2dcb5
2024-06-18 12:39:26 +08:00
Jonery
3a5eacb4cf Support distributed BAdam.
Former-commit-id: 0f72aac8c9227e33ad20d2b1641b1c9faae16a5f
2024-06-18 12:27:47 +08:00
hiyouga
19bf21efba lint
Former-commit-id: 24c160df3d575843e5ad5f1b47246d04430a79f0
2024-06-17 22:35:56 +08:00
hiyouga
3d85217464 update chat engine #4335
Former-commit-id: 7857c0990b37d37e58691257eea13fe5e244aaa0
2024-06-17 19:07:17 +08:00
Jonery
5d59f6562a Merge remote-tracking branch 'upstream/main'
Former-commit-id: ea1f3ba5e030504e07053484f50f4cbdb37808bc
2024-06-17 18:44:51 +08:00
Jonery
756566342d adapt for badam with ds zero3
Former-commit-id: 33b437277846d4f0b64c13a0bc892ef4f345a21e
2024-06-17 18:18:10 +08:00
hiyouga
7ef169ed39 fix #4326
Former-commit-id: e2665e71c7428014d46d91542b01a58c1064d05a
2024-06-17 18:17:48 +08:00
hoshi-hiyouga
06bbc29614 Update parser.py
Former-commit-id: 29c1f31baa442e35714b18b7e51896274a828cae
2024-06-16 02:57:00 +08:00
hiyouga
ce4a27a5f7 fix tol
Former-commit-id: 46093b5786611d99adf1fd3d42926a728fc629f8
2024-06-16 01:38:44 +08:00
hiyouga
f25b8626bf support pissa
Former-commit-id: 8c1046d78ac6c8f9429b73617e35e1eccb35138f
2024-06-16 01:08:12 +08:00
hiyouga
c0c6b8075a tiny fix
Former-commit-id: 38b6b0f52edeb8ba45aa03b415b3c0c1b0e0c1e4
2024-06-16 01:06:41 +08:00
hiyouga
96b82ccd4d use fixture
Former-commit-id: 80a9e6bf94cf14fa63e6b6cdf7e1ce13722c8b5e
2024-06-15 20:06:17 +08:00
hiyouga
8053929b20 add tests
Former-commit-id: 1b834f50be64ae9b5123da0e6f528cfbd5167477
2024-06-15 19:51:20 +08:00
hiyouga
f0d6e63f55 add minicpm #4227
Former-commit-id: 572d8bbfdd73c1a00b432f0d0411f46fad6aa1a6
2024-06-15 17:58:52 +08:00
hiyouga
2946153cea add license
Former-commit-id: d87108daa68bd40174b262be1ca65fe6e1b7ab56
2024-06-15 17:54:33 +08:00
hiyouga
fcbfa70c19 disable DP
Former-commit-id: d519b4d76d39b21a21b1d2f6f7ce6b3af9525d03
2024-06-15 04:57:19 +08:00
hiyouga
ba9aa7e2aa fix #4292
Former-commit-id: 9092f963dba6f2e0eeade53b5b35e6b770f8348e
2024-06-15 04:47:13 +08:00
hiyouga
ab66ae8cd2 fix #4295
Former-commit-id: 78589cf90c6e12e612f269b1c771f19f3dad83d2
2024-06-15 04:34:55 +08:00
hiyouga
a3f4925c2c add test cases
Former-commit-id: b27269bd2b52fb9d43cde8a8b7f293099b0127a2
2024-06-15 04:05:54 +08:00
hiyouga
27777c8e68 add quant check in webui export tab
Former-commit-id: c94e6c9411cc1165ea8180d377611a3ae47956e6
2024-06-13 03:19:18 +08:00
hiyouga
8fccaf20c5 fix #4221
Former-commit-id: 6baafd4eb3147ad9f7d2952b8eb27c5486940f36
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: cf9f2d6c42b5a37038c9eededbb767eae6a3f67d
2024-06-13 02:25:50 +08:00
hiyouga
833aa324c2 clean code
Former-commit-id: 2ed8270112755971e3f2dfd2f29c5939b077330a
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: 1f23f25226f43bb2b2116474b9c6ab2d72e7e260
2024-06-13 01:54:02 +08:00
hiyouga
99ce085415 fix lint
Former-commit-id: 713fde4259233af645bade7790211064a07a2a6f
2024-06-13 00:48:44 +08:00
hzhaoy
65f2ba3802 adapt vllm==0.5.0
Former-commit-id: 8fb6366ebec432c1333c80eb51007460ac5896bd
2024-06-12 18:29:03 +08:00
hiyouga
f8497921fe fix #4242
Former-commit-id: 577de2fa078ee62d61bca24b75fa59590e2ef66b
2024-06-12 16:50:11 +08:00
Arthur Kim
bebca6d01c Support vllm==0.5.0
Former-commit-id: d65a3f7cb6dcd34e9a3ff9e30dffc52a7671d50b
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: 9049aab911fa3fbe9cd463ae3805f81b484da052
2024-06-11 17:06:10 +08:00
hoshi-hiyouga
bf3de9bfe8 Update pretrain.py
Former-commit-id: 0c292332374fb96c3fc753abde42d070a0c1dca8
2024-06-11 17:02:14 +08:00
hiyouga
8c574eb3cb fix deepspeed version
Former-commit-id: cca6f351081903ca3b5f79f10accc1bbbae0ee61
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: 6979f3f8480755604d8aea8164f6418126e094c5
2024-06-11 16:23:40 +08:00
hiyouga
5834651c4a fix #4198
Former-commit-id: 89f2bd8c8c035181927bd530a7ffc733407d674c
2024-06-11 15:38:38 +08:00
hiyouga
53de7f7cc3 tiny fix
Former-commit-id: 90e14a960d1437a16d35dbabbb8aa50714583d3a
2024-06-11 12:48:53 +08:00
hiyouga
e3baa5aa08 tiny fix
Former-commit-id: 3f24337a8a995b145b1e8075bc23878eaa363844
2024-06-11 01:04:16 +08:00
hiyouga
d6632fefc9 set dev version
Former-commit-id: 91e62a098fd997d0d1d12baef64d089aabc01fba
2024-06-11 00:50:53 +08:00
hiyouga
75e1bbf128 release v0.8.1
Former-commit-id: 2b6ebd6b51133cf114d6f0e8605ad2bb26aa6d65
2024-06-11 00:44:26 +08:00
hiyouga
2f164c2c41 fix #4160
The split heads should be concatenated in dim=2


Former-commit-id: a793e8456b664ea0b48f0ba162999f18d06b4c2f
2024-06-11 00:37:17 +08:00
hiyouga
144544cd37 update evaluator
Former-commit-id: 0012762b04d4082a3a7d98889cc3024adc92fc44
2024-06-10 23:56:00 +08:00