423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-14 19:06:26 +08:00
Code Issues Packages Projects Releases Wiki Activity
532 Commits 1 Branch 34 Tags
4a0be64ae64e256789e53434fe1c07ee635a7c48
Commit Graph

395 Commits

Author SHA1 Message Date
hiyouga
c4f1d98a1c fix saving custom code 
Former-commit-id: 1e1358431d
 2023-07-16 18:04:41 +08:00
hiyouga
20e4bf3b5b fix callback 
Former-commit-id: 552d773dad
 2023-07-15 22:01:43 +08:00
hiyouga
22e979c482 update stream_chat 
Former-commit-id: 8528a84e74
 2023-07-15 19:51:02 +08:00
hiyouga
b8b38a9ade create chat model 
Former-commit-id: 657cf0f55a
 2023-07-15 19:26:20 +08:00
hiyouga
8ba0996a53 Update callbacks.py 
Former-commit-id: d640c5545f
 2023-07-15 17:39:16 +08:00
hiyouga
70b5232f9a fix callback 
Former-commit-id: 22d9a9c2af
 2023-07-15 17:18:16 +08:00
hiyouga
a696148d6b modity code structure 
Former-commit-id: f751376613
 2023-07-15 16:54:28 +08:00
hiyouga
7ea072536b fix eval and pred loss 
Former-commit-id: c30db9f1f0
 2023-07-14 13:11:57 +08:00
hiyouga
32ec440d2e fix pretrain 
Former-commit-id: a04115ec27
 2023-07-13 23:41:54 +08:00
hiyouga
2b0fced03b fix Baichuan-13B 
Former-commit-id: 08439d29b2
 2023-07-13 23:08:45 +08:00
Jinghuan Shang
d42d175670 Fix typo in common.py 
lastest -> latest

Former-commit-id: dc1e8b7181
 2023-07-11 18:03:53 -04:00
hiyouga
925a026853 fix sft encode 
Former-commit-id: b2f7cb4465
 2023-07-11 19:50:33 +08:00
hiyouga
685ba1e02e add baichuan template 
Former-commit-id: 1af031c02b
 2023-07-11 18:57:50 +08:00
hiyouga
c812429011 update api to match langchain 
Former-commit-id: 84a06318d4
 2023-07-07 20:35:39 +08:00
hiyouga
8b4ef062b7 support InternLM 
Former-commit-id: a2f507c562
 2023-07-07 11:02:28 +08:00
hiyouga
50a27509a3 fix rouge score 
Former-commit-id: caa00d3ac2
 2023-07-06 14:28:34 +08:00
hiyouga
22fa516bd5 fix streaming response in API 
Former-commit-id: 4abd2485e1
 2023-07-05 22:42:31 +08:00
hiyouga
bcd7493212 fix freeze tuning 
Former-commit-id: e6603977f6
 2023-07-05 21:18:28 +08:00
hiyouga
265dc1b6a0 fix bug in PPO stage 
Former-commit-id: a2ba69183b
 2023-07-05 19:14:10 +08:00
hiyouga
7ba52f5b6e fix compute dtype 
Former-commit-id: 8e3540c62d
 2023-07-05 15:13:00 +08:00
hiyouga
c87910ada3 support falcon model #72 
Former-commit-id: c136f362c1
 2023-07-05 15:00:06 +08:00
hiyouga
9e8854535b fix bleu score 
Former-commit-id: cac87fd553
 2023-07-05 00:11:21 +08:00
hiyouga
023f9367fc set use_cache before saving model 
Former-commit-id: 395ed1cf1b
 2023-07-04 23:18:20 +08:00
hiyouga
b9d56b2ac5 fix seq2seq predictions 
Former-commit-id: 65e9ce2cdd
 2023-07-04 22:56:51 +08:00
hiyouga
4ec1bff116 fix typo 
Former-commit-id: 92fa515e97
 2023-06-30 10:09:59 +08:00
hiyouga
1ce7b5e0f3 update loading logic 
Former-commit-id: 4d0fddba21
 2023-06-28 12:07:16 +08:00
hiyouga
2ff577810a fix loading best model 
Former-commit-id: 0a46313cca
 2023-06-28 01:55:12 +08:00
hiyouga
c3cd2067b2 fix RM accuracy 
Former-commit-id: 7826a8ca77
 2023-06-28 01:40:13 +08:00
hiyouga
c5ec4eaef5 tiny fix 
Former-commit-id: 450910c1db
 2023-06-27 23:54:24 +08:00
hiyouga
e877b8d55b fix initializing data arguments 
Former-commit-id: 18f87c1b25
 2023-06-27 22:50:23 +08:00
hiyouga
307f5866e9 support save full model, replace BOS token 
Former-commit-id: 2e01abfda5
 2023-06-27 21:40:11 +08:00
hiyouga
86a7b2dc5d fix decoding in seq2seq 
Former-commit-id: 1c732e2537
 2023-06-27 19:33:08 +08:00
hiyouga
c145ca4ad6 fix generation in seq2seq.py 
Former-commit-id: 1175948029
 2023-06-26 18:07:06 +08:00
hiyouga
8f1d99c926 support prefixes, loading multiple local files 
Former-commit-id: cec9760eb8
 2023-06-26 15:32:40 +08:00
hiyouga
e4a869dc42 update api 
Former-commit-id: f030b09924
 2023-06-26 13:39:57 +08:00
hiyouga
cf29a9af35 update readme 
Former-commit-id: 0697643358
 2023-06-23 00:17:05 +08:00
hiyouga
0c7eb90f6b update API 
Former-commit-id: 614d3a996c
 2023-06-22 20:46:24 +08:00
hiyouga
620cd2eb7e match api with OpenAI format 
Former-commit-id: 76ecb8c222
 2023-06-22 20:27:00 +08:00
Bun
cd066afa7b Compatible with OpenAI API. 
Former-commit-id: 6e4db0903f
 2023-06-21 14:45:04 +08:00
hiyouga
eeb78bd75c add default template 
Former-commit-id: f621f7631a
 2023-06-16 21:12:17 +08:00
hiyouga
653ce9397e fix freeze layers 
Former-commit-id: a6c4b141cd
 2023-06-16 17:38:21 +08:00
hiyouga
36ea46e85c add source prefix 
Former-commit-id: fc4d8155b3
 2023-06-16 16:32:17 +08:00
hiyouga
c6d56e7109 support loading lora from hub 
Former-commit-id: 0574b590ef
 2023-06-16 00:02:17 +08:00
hiyouga
a68808d6d9 support baichuan model 
Former-commit-id: 0cee6ad67f
 2023-06-15 16:02:01 +08:00
hiyouga
50494db8d6 fix bug in template vanilla 
Former-commit-id: c527399424
 2023-06-15 14:36:55 +08:00
hiyouga
dd1e7ed3cf add BOS token in pre-training 
Former-commit-id: d668f8b501
 2023-06-15 01:46:17 +08:00
hiyouga
3419396945 support multiturn training like FastChat 
Former-commit-id: b6faf0207d
 2023-06-14 22:27:39 +08:00
hiyouga
ca90a1e6d9 fix loading valuehead 
Former-commit-id: 875e8e2349
 2023-06-13 11:13:06 +08:00
hiyouga
c92bfb158f fix generating args 
Former-commit-id: 531a3764d9
 2023-06-13 01:33:56 +08:00
hiyouga
1fbda5d139 support RM metrics, add generating Args 
Former-commit-id: cec6524d6b
 2023-06-12 15:48:48 +08:00