Commit Graph

2127 Commits

Author SHA1 Message Date
Jonery
756566342d adapt for badam with ds zero3
Former-commit-id: 33b4372778
2024-06-17 18:18:10 +08:00
hiyouga
7ef169ed39 fix #4326
Former-commit-id: e2665e71c7
2024-06-17 18:17:48 +08:00
hiyouga
0a40ee5444 Update wechat.jpg
Former-commit-id: 72471ee046
2024-06-17 17:49:03 +08:00
hiyouga
004f289074 tiny fix
Former-commit-id: 2bf2863a58
2024-06-17 17:47:25 +08:00
胡翀
8ab2d707e5 Update requirements.txt
add pandas version requirements

Former-commit-id: 12869c3ede
2024-06-17 16:45:57 +08:00
Eli Costa
191dac26c0 Fix Dockerfile
Adds the commands to correctly execute LLama-Factory servers

Former-commit-id: df12621dae
2024-06-16 19:16:23 -03:00
Eli Costa
d7459853d8 Update README_zh.md
Fix details tag in datasets menus

Former-commit-id: 3ec57ac239
2024-06-16 11:34:31 -03:00
Eli Costa
ee30db72a3 Update README_zh.md
Add Magpie and WebInstruct to README

Former-commit-id: 82d5c5c1e8
2024-06-16 11:22:06 -03:00
Eli Costa
26e942b0ad Update README.md
Add Magpie and Webinstruct to README

Former-commit-id: 103664203c
2024-06-16 11:19:25 -03:00
Eli Costa
6bbb8b4cd8 Add Magpie and Webinstruct dataset samples
Adds two dataset samples claimed superior performance: Magpie (from Allen AI) and Webinstruct (from TIGER-Lab).

Former-commit-id: 74e49cca95
2024-06-15 19:31:56 -03:00
ancv
988231026a update packing with sdpa and eager attention mode
Former-commit-id: 238f5c3d99
2024-06-16 02:25:47 +07:00
hoshi-hiyouga
06bbc29614 Update parser.py
Former-commit-id: 29c1f31baa
2024-06-16 02:57:00 +08:00
hiyouga
5769cc8d06 update pr template
Former-commit-id: 0a2ec5fe20
2024-06-16 01:43:43 +08:00
hoshi-hiyouga
0ddf7bd28a Merge pull request #4307 from hiyouga/pissa
Support pissa

Former-commit-id: b7b5892a34
2024-06-16 01:41:50 +08:00
hiyouga
ce4a27a5f7 fix tol
Former-commit-id: 46093b5786
2024-06-16 01:38:44 +08:00
hiyouga
a8655f5c08 Update tests.yml
Former-commit-id: 7f3c19e3ab
2024-06-16 01:22:23 +08:00
hiyouga
2d2c78d66c increase tol
Former-commit-id: de43bee0b0
2024-06-16 01:21:06 +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
ancv
9d9f8c6531 remove some unused params
Former-commit-id: 04315c3d92
2024-06-15 23:00:55 +07:00
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
4dcd124dbd update readme
Former-commit-id: acd84ce535
2024-06-15 05:13:16 +08:00
hiyouga
19ea51e460 fix #4271
Former-commit-id: f1aa6a411a
2024-06-15 05:11:33 +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
d4ce280fbc Update README.md
Former-commit-id: 2d43b8bb49
2024-06-13 16:02:21 +08:00
hiyouga
f81a839197 update examples
Former-commit-id: 892e561c28
2024-06-13 03:26:10 +08:00
hiyouga
27777c8e68 add quant check in webui export tab
Former-commit-id: c94e6c9411
2024-06-13 03:19:18 +08:00
hiyouga
4c40171c55 Update llama3_full_sft_ds3.yaml
Former-commit-id: a19cdd39fe
2024-06-13 03:16:20 +08:00
hiyouga
0926d81053 update examples
Former-commit-id: b6e008c152
2024-06-13 03:15:06 +08:00
hiyouga
8fccaf20c5 fix #4221
Former-commit-id: 6baafd4eb3
2024-06-13 02:48:21 +08:00
hiyouga
c51f5c2a0a update wechat
Former-commit-id: 9419f96609
2024-06-13 02:31:45 +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
e89d1b1ec3 add neo-sft dataset
Former-commit-id: c7a5620ccc
2024-06-13 01:00:56 +08:00
hiyouga
99ce085415 fix lint
Former-commit-id: 713fde4259
2024-06-13 00:48:44 +08:00
hiyouga
b2b0b96051 fix docker compose usage
Former-commit-id: 947a34f53b
2024-06-13 00:07:48 +08:00
hzhaoy
65f2ba3802 adapt vllm==0.5.0
Former-commit-id: 8fb6366ebe
2024-06-12 18:29:03 +08:00
hiyouga
77e4dc255f update readme
Former-commit-id: 2ce2e5bc47
2024-06-12 17:39:12 +08:00
hiyouga
f8497921fe fix #4242
Former-commit-id: 577de2fa07
2024-06-12 16:50:11 +08:00
hoshi-hiyouga
bc5e97295e Merge pull request #4234 from kimdwkimdw/patch-1
Support vllm==0.5.0

Former-commit-id: 656b2bbdaf
2024-06-12 16:39:09 +08:00
Arthur Kim
bebca6d01c Support vllm==0.5.0
Former-commit-id: d65a3f7cb6
2024-06-12 16:49:12 +09:00
ancv
045eb155a2 implement efficient packing without cross-contamination attention
Former-commit-id: b2c367bc61
2024-06-12 11:56:01 +07:00
codingma
c7e021a837 update wechat_npu.jpg
Former-commit-id: 557891debb
2024-06-12 10:39:05 +08:00