1224 Commits

Author SHA1 Message Date
codingma
b7cc559649 add empty line
Former-commit-id: 1c6c2e611d10e9fa662e3f4e1e7d23b80ae496cb
2024-04-07 18:28:08 +08:00
codingma
7497f4f05b rename template to breeze
Former-commit-id: 1223e6358dab52b4e1505057f1b16fd9d527c79e
2024-04-07 18:27:20 +08:00
hoshi-hiyouga
47dc54b9ff Merge pull request #3160 from sliderSun/main
support Qwen1.5-32B

Former-commit-id: 1e5a5882dd494c3e9cf5eae2e0a485ce49d1863c
2024-04-07 18:00:40 +08:00
codingma
a61e69c0d9 rename template to breeze
Former-commit-id: 1d894e7cfb73b8a29dababb554d051bd50e4f01d
2024-04-07 11:39:54 +08:00
codingma
34d061f963 support https://github.com/hiyouga/LLaMA-Factory/issues/3152
Former-commit-id: 708f0ab4b0aa72e2c73ca36eb9ed058910e43092
2024-04-07 11:34:01 +08:00
sliderSun
6c9e8e89cf fix spell error
Former-commit-id: e6d36a2e593ebc1193b1735075c4ddb5d9f54990
2024-04-07 10:59:15 +08:00
sliderSun
3bdbe17702 support Qwen1.5-32B
Former-commit-id: c419adf1697b92520342f4ffa697c84bf19ca37d
2024-04-07 10:56:03 +08:00
sliderSun
6eb424adbe support Qwen1.5-32B
Former-commit-id: 8f2c67b95a8e177eb4096382417a70cacba38e90
2024-04-07 10:26:13 +08:00
hiyouga
ff005dc66e update readme
Former-commit-id: 1cf15547e2420a3e5f7a969c21c10c7fbdfc71fe
2024-04-07 00:48:24 +08:00
hiyouga
46a76afd44 update examples
Former-commit-id: de40ad62ba3d4c74c69de97b39cc79786ac28f0f
2024-04-04 14:48:21 +08:00
hiyouga
9e2af508bb tiny fix
Former-commit-id: 70aceecb27e72095c05462d01f956061669b267e
2024-04-04 02:19:03 +08:00
hiyouga
1afadd9975 back to gradio 4.21 and fix chat
Former-commit-id: 695734a40a702ea059d855da54080cc8d161e41a
2024-04-04 02:07:20 +08:00
hiyouga
b112959309 fix bug in latest gradio
Former-commit-id: 44a962862b4a74e50ef5786c8d5719faaa65f63f
2024-04-04 00:55:31 +08:00
hiyouga
f939dce8d7 fix requires for windows
Former-commit-id: 5e25fae40b7ea9cfa72717efbe3677199ca9608f
2024-04-03 21:56:43 +08:00
hiyouga
d97150c571 fix resize vocab at inference #3022
Former-commit-id: c243720b89eec0af2872fa3c7980a0026d893f4d
2024-04-03 18:14:24 +08:00
hiyouga
99ed1657db fix #3116
Former-commit-id: b7256aa33d761280751518c20f29f9b8ea3fb025
2024-04-03 14:47:59 +08:00
hiyouga
2e2ebc0986 update vllm example
Former-commit-id: 2df6d2eacfa27ebc69455696b93649624c1facbe
2024-04-02 22:45:20 +08:00
hiyouga
54773b6116 update readme
Former-commit-id: 7ea7333b51be6b1120fc0b13675f5a0ac3c5a12b
2024-04-02 22:17:48 +08:00
hiyouga
aef4b0d4a3 update examples
Former-commit-id: 2715cfe20f6f4532bebaa47b80ccd5df43d6a490
2024-04-02 21:09:25 +08:00
hiyouga
1317dd28a3 add zh readme
Former-commit-id: 389a170a4d42c56c71c0e17bbe018c4cb1983b5a
2024-04-02 20:58:45 +08:00
hiyouga
037e8518d5 update examples
Former-commit-id: c078582a759f6bce6e760cd39a05883f7eb194fe
2024-04-02 20:51:21 +08:00
hiyouga
b1401c70be update examples
Former-commit-id: bf36b16e48d6438de6d0b2f2bfe33f7895699b9d
2024-04-02 20:41:49 +08:00
hiyouga
06af770c99 update readme
Former-commit-id: 9b8e7ccdab167f53fb897e1940562682324e8ff0
2024-04-02 20:37:37 +08:00
hiyouga
c95e06b34a update readme
Former-commit-id: 0c73d3c8a5762a8f119b27322ffd52a61de6fe38
2024-04-02 20:22:11 +08:00
hiyouga
75819c1220 simplify readme
Former-commit-id: 0da6ec2d516326fe9c7583ba71cd1778eb838178
2024-04-02 20:07:43 +08:00
hiyouga
76ba7b51c1 add moe aux loss control #3085
Former-commit-id: c9187ebc944e2de454ace3304b7d28eabb1b1a81
2024-04-02 14:26:31 +08:00
hiyouga
e645b9f42b fix #3022
Former-commit-id: dac2f617bda9470ac8d85c7e9def09cc04970506
2024-04-02 13:58:39 +08:00
hiyouga
9ff9bd9b70 Update SECURITY.md
Former-commit-id: e22217c75421a89fd7e2ada62ce0e08245dd05e7
2024-04-01 23:30:03 +08:00
hiyouga
f0e657ec99 set dev version
Former-commit-id: 922ecae89210e5b8d62d78774f123a6d75c525ba
2024-04-01 23:24:08 +08:00
hiyouga
357a32d7a0 fix #3083
Former-commit-id: ff9a3f73961a362d0ddc22079f80a85465fffda8
2024-04-01 22:53:52 +08:00
hiyouga
ff301c08d6 add qwen1.5 moe
Former-commit-id: 3ea94f0d12cec25ac694a2c4ae8971c356990b61
2024-04-01 21:49:40 +08:00
hiyouga
8365522ce2 fix #3077
Former-commit-id: d0340391e8075cff0d84b3ef879c2101b66ca1dc
2024-04-01 21:35:18 +08:00
hiyouga
4e3ee3b703 support infer 4bit model on GPUs #3023
Former-commit-id: 950a9dab9055839990656b2b40956792b253573d
2024-04-01 17:34:04 +08:00
hiyouga
99294220db update webui
Former-commit-id: e96d260917a35ad2068f7b28b4f0b334b808ccc2
2024-04-01 16:23:28 +08:00
hiyouga
0116675349 fix ORPO loss
Former-commit-id: 5544ddde9087f00f9e20b78d0079f20c2f5d1604
2024-04-01 14:42:41 +08:00
hiyouga
bf10e23dc8 fix IPO and ORPO loss
Former-commit-id: fc27955732aedbb12003faf19b760e2768b228f2
2024-04-01 14:37:53 +08:00
hiyouga
f59dd028e5 fix plots
Former-commit-id: 81355671296b84d438967463bb2a92934ff31aae
2024-03-31 19:43:48 +08:00
hiyouga
899e9e091c use log1p in orpo loss
https://github.com/huggingface/trl/pull/1491

Former-commit-id: 3b15d495264b00a4f8716bafea334778874963d7
2024-03-31 19:27:08 +08:00
hiyouga
cd05e1bb8b update readme
Former-commit-id: 297b01f16ac78cde15a5d85a9a5b82ea20bfaf23
2024-03-31 18:46:34 +08:00
hoshi-hiyouga
de008eafcb Merge pull request #3066 from hiyouga/orpo
support ORPO

Former-commit-id: fd4d3d29a9fae289f3bd0c4ce00656e4ccbec2e1
2024-03-31 18:42:48 +08:00
hiyouga
cdde212184 support orpo in webui
Former-commit-id: dd5cc78d4fb18dd0a2e9d57f0f046cfe9f0dc2c9
2024-03-31 18:34:59 +08:00
hiyouga
e6c7e6e667 support ORPO
Former-commit-id: f44a4c27e2461cdaa1b16865f597a31033c0e6d9
2024-03-31 18:29:50 +08:00
hiyouga
0c96919aa5 tiny fix
Former-commit-id: ba4a9b3c01e2f7467fbc5be268f47c0d003caa65
2024-03-31 00:10:29 +08:00
hoshi-hiyouga
7567e11958 Merge pull request #3057 from marko1616/bugfix/lora-model-merge
Fix Llama model save for full param train

Former-commit-id: 18303e34d07dbf4c2dd9bac03243a3ed38582515
2024-03-31 00:07:20 +08:00
marko1616
e9060f37e4 fix blank line contains whitespace
Former-commit-id: 7bc3bcc64353d5a1d4870c6a9509b64cff710492
2024-03-30 23:46:55 +08:00
marko1616
fb6e653443 Fix Llama model save for full param train
Former-commit-id: ca17b5db4f97c3ec9fe2004877f150e8f51ab4b5
2024-03-30 23:45:04 +08:00
hiyouga
d7ea73957f support save args in webui #2807 #3046
some ideas are borrowed from @marko1616


Former-commit-id: b5a062aa2d4a37670007e8b3dae5b6f5b7ffb15c
2024-03-30 23:09:12 +08:00
hoshi-hiyouga
13163e50c5 Merge pull request #3053 from lealaxy/main
Fix pile dataset download config

Former-commit-id: 899fa035bd03eda66bd4f049b18dcb1904d10c29
2024-03-30 20:41:43 +08:00
hiyouga
0f38af9365 upgrade gradio to 4.21.0
Former-commit-id: 63eecbeb967d849e1d03d8d03fb6421c0ee89257
2024-03-30 20:37:08 +08:00
li.yunhao
e6e3571232 fix pile datset hf hub url
Former-commit-id: c06f71f74ee1b177617417d151185757fd4359f5
2024-03-30 16:06:10 +08:00