Commit Graph

1570 Commits

Author SHA1 Message Date
hiyouga
11a6c8a9a0 fix #1909
Former-commit-id: 0bbf7118df
2023-12-23 14:42:20 +08:00
hiyouga
18c6e6fea9 update readme
Former-commit-id: 0ad86a4f62
2023-12-23 02:17:41 +08:00
hiyouga
a7fc20cb2d fix unsloth dtype
Former-commit-id: 779cfefb78
2023-12-23 01:59:49 +08:00
hiyouga
938c4cb132 fix dpo trainer
Former-commit-id: 074745b170
2023-12-23 01:51:55 +08:00
hiyouga
bf872424da llama board: add unsloth
Former-commit-id: 9a18a85639
2023-12-23 00:35:53 +08:00
hiyouga
f0d405f392 support unsloth
Former-commit-id: 7aad0b889d
2023-12-23 00:14:33 +08:00
hoshi-hiyouga
940824e306 Merge pull request #1953 from ShaneTian/model-load-bf16
Fix slow model initialization in bfloat16 dtype.

Former-commit-id: 315b8367cb
2023-12-22 17:29:54 +08:00
ShaneTian
3eaabe12aa Fix slow model initialization in bfloat16 dtype.
Former-commit-id: d032daa4bd
2023-12-22 16:27:28 +08:00
hiyouga
ce79528bb1 fix param type
Former-commit-id: ba69378841
2023-12-21 17:33:01 +08:00
hiyouga
fee0fef052 fix ds zero3 check
Former-commit-id: 083355fc05
2023-12-21 01:19:22 +08:00
hiyouga
de6be321b9 match version
Former-commit-id: af0194e6d9
2023-12-20 22:17:35 +08:00
hoshi-hiyouga
1df1a44e9d Merge pull request #1932 from ShaneTian/main
Update transformers to 4.36.2 to resolve multi-node saving bug.

Former-commit-id: ba4d32bf59
2023-12-20 22:13:28 +08:00
ShaneTian
69cb0038f0 Update transformers to 4.36.2 to resolve bug when saving a checkpoint in the multi-node setting.
Former-commit-id: 390f0caf7f
2023-12-20 22:00:41 +08:00
hiyouga
0a69665525 Update wechat.jpg
Former-commit-id: 7910dbae92
2023-12-20 19:24:37 +08:00
hiyouga
9337568e23 fix stop words
Former-commit-id: dec360d5ae
2023-12-20 19:06:43 +08:00
hiyouga
622d31e398 fix yi template #1895
Former-commit-id: 5af8841c4f
2023-12-20 18:58:16 +08:00
hiyouga
23a875a8b1 improve quantization
Former-commit-id: 624cc21281
2023-12-20 18:27:16 +08:00
hiyouga
c1233ab65f add max_memory for gptq #1923
Former-commit-id: c4a3977ad7
2023-12-20 18:15:17 +08:00
hiyouga
82a79e9fdf fix #1073 #1462 #1735 #1908
Former-commit-id: 31165a9822
2023-12-20 17:15:40 +08:00
hiyouga
f64be8ee84 optimize data loading logic
Former-commit-id: ec1fe1daa9
2023-12-20 16:15:41 +08:00
hiyouga
633624dc3c fix #1909
Former-commit-id: c6abbbfe90
2023-12-20 16:11:07 +08:00
hiyouga
a862ce636f fix mixtral inference #1821
Former-commit-id: f86857bd9e
2023-12-20 15:11:15 +08:00
hiyouga
e06b9c4fa1 fix #1900
Former-commit-id: 0c6ab7c75e
2023-12-19 17:21:46 +08:00
hiyouga
54e58adf09 update readme
Former-commit-id: edb7d177c2
2023-12-18 22:29:45 +08:00
hiyouga
3981927d6b add codegeex template
Former-commit-id: a67a440644
2023-12-18 19:52:35 +08:00
hiyouga
51c636db54 add xverse-65B-2 model
Former-commit-id: 2df923540c
2023-12-18 19:24:09 +08:00
hiyouga
1af13cb737 add models
Former-commit-id: 709ac8870a
2023-12-18 19:09:31 +08:00
hiyouga
5a199af387 fix tokenizer for Yi chat models #1617 #1875
Former-commit-id: 71a9c16171
2023-12-18 17:18:11 +08:00
hiyouga
dee19b11ba update readme
Former-commit-id: 2b4e5f0d32
2023-12-18 15:46:45 +08:00
hiyouga
16cc0321f2 fix llama board
Former-commit-id: c46879575f
2023-12-16 22:17:37 +08:00
hiyouga
8154b4bdf6 fix #1742
Former-commit-id: 870426ff70
2023-12-16 20:50:45 +08:00
hiyouga
397f6bb615 add xverse-65b-chat model
Former-commit-id: 7ae6919b9b
2023-12-16 20:21:29 +08:00
hiyouga
ff5f57bfbf set version
Former-commit-id: 328ad06bd4
2023-12-16 20:17:51 +08:00
hiyouga
7c362509a6 add noisy mean initialization #1815
Former-commit-id: a66186b872
2023-12-16 19:47:51 +08:00
hiyouga
4e75ca1222 support dpo-ftx
Former-commit-id: b87c74289d
2023-12-16 19:21:41 +08:00
hiyouga
f0f9d253d8 support autogptq in llama board #246
Former-commit-id: 71389be37c
2023-12-16 16:31:30 +08:00
hoshi-hiyouga
adafb38cb8 Merge pull request #1868 from yhyu13/improve_hfargparser
Improve logging for unknown args

Former-commit-id: 93f64ce9a8
2023-12-16 16:06:09 +08:00
yhyu13
cc91724507 Use llmtuner logger
Former-commit-id: fc70a92cb6
2023-12-16 07:15:27 +00:00
yhyu13
362e3c913f Improve logging for unknown args
Former-commit-id: 26817143ff
2023-12-16 05:16:29 +00:00
hiyouga
7db6fe4754 update tips
Former-commit-id: 3551171d49
2023-12-15 23:52:50 +08:00
hiyouga
9a88387b91 fix #1770
Former-commit-id: 439a26c276
2023-12-15 23:50:15 +08:00
hiyouga
7dbc670902 support quantization in export model
Former-commit-id: 3524aa1e58
2023-12-15 23:44:50 +08:00
hiyouga
2db4cfab40 update dc link
Former-commit-id: 87ef3f47b5
2023-12-15 22:11:31 +08:00
hoshi-hiyouga
68b1500c41 Merge pull request #1864 from hiyouga/dev
Refactor hyper-parameters of adapters and model loader

Former-commit-id: e2bd597b3c
2023-12-15 22:06:56 +08:00
hiyouga
329576a5b4 fix bug
Former-commit-id: 00c77104f8
2023-12-15 21:54:02 +08:00
hiyouga
f32c8614c2 fix bug
Former-commit-id: 9e509b99af
2023-12-15 21:49:26 +08:00
hiyouga
d24d2f0458 add configurer
Former-commit-id: 2740aa9cbb
2023-12-15 21:46:40 +08:00
hiyouga
bd03307bbd refactor adapter hparam
Former-commit-id: 0716f5e470
2023-12-15 20:53:11 +08:00
hiyouga
6a186d4386 add loftq
Former-commit-id: d4c351f1ec
2023-12-14 21:53:56 +08:00
hiyouga
e55e32efc4 fix valuehead model
Former-commit-id: bfdee1608f
2023-12-14 20:15:20 +08:00