github
/
ChatGLM-6B
mirror of https://github.com/THUDM/ChatGLM-6B
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
238 Commits
5 Branches
0 Tags
26 MiB
Commit Graph

52 Commits (70e015654c56b20cdce2f6637dae75ccfea0a7b8)

Author SHA1 Message Date
duzx16 7607cfe585 Fix turn_idx in eval 2023-04-12 23:41:37 +08:00
duzx16 f06df225dd Fix turn_idx 2023-04-12 23:34:44 +08:00
duzx16 da626f8b23 Add instruction for pre_seq_len 2023-04-12 22:42:36 +08:00
rainatam a1d9dcc517 Update README 2023-04-12 21:11:29 +08:00
rainatam 1a368afd26 Update README 2023-04-12 16:43:34 +08:00
rainatam 3736c1ae98 Update README 2023-04-12 12:28:25 +08:00
duzx16 57e9da3822 Merge branch 'main' of github.com:THUDM/ChatGLM-6B 2023-04-12 09:49:20 +08:00
duzx16 79e4d8ba8a Remove todo 2023-04-12 09:49:14 +08:00
rainatam 0c2806fea8 Fix typo 2023-04-11 13:48:54 +08:00
rainatam 75aa887c20 Update LoRA evaluation results 2023-04-11 01:06:11 +08:00
rainatam 166a6e70f1 Update LoRA evaluation results 2023-04-11 01:04:03 +08:00
rainatam ec5f258de9 Update evaluation results 2023-04-10 22:31:08 +08:00
rainatam 173ccd8d27 Update trainer 2023-04-10 19:40:21 +08:00
rainatam 2073ac75d4 Update README 2023-04-10 18:43:17 +08:00
rainatam 2a5250ffcb Update trainer 2023-04-10 18:32:40 +08:00
rainatam 47a5ec121e Add deepspeed finetuning scripts 2023-04-10 17:28:27 +08:00
rainatam cbb9f44e30 Save PrefixEncoder params only 2023-04-10 17:26:17 +08:00
Vinlic科技 d694a0087e
错别字修正 2023-04-07 14:27:02 +08:00
duzx16 fd3d40fa9f Merge branch 'main' of github.com:THUDM/ChatGLM-6B 2023-04-06 22:43:10 +08:00
duzx16 ea682a6f51 Update default hyperparameters 
Remove hardcode token id
 2023-04-06 22:42:41 +08:00
rainatam 0cf3d08841 Update README 2023-04-06 22:30:30 +08:00
rainatam a1ecafd91f Update README 2023-04-06 20:47:32 +08:00
rainatam ed79244725 Update README 2023-04-06 20:46:26 +08:00
rainatam 83ef59b146 Merge branch 'main' of https://github.com/THUDM/ChatGLM-6B into main 2023-04-06 20:23:46 +08:00
rainatam 1cbe2d1981 Remove logging 2023-04-06 20:22:56 +08:00
rainatam 5865924cc6 Add training for chat data 2023-04-06 20:21:29 +08:00
duzx16 6792ca6805 Add English readme 2023-04-06 17:55:31 +08:00
duzx16 7131d29f2d Add English readme 2023-04-06 17:51:20 +08:00
rainatam a9fc018444 Update evaluation results and bleu score function 2023-04-06 15:16:36 +08:00
Qingsong Lv 5de0055408 fix finetune pad bug and add sat readme 2023-04-03 11:27:28 +00:00
duzx16 ed9631a96b Add deploement for ptuning model 2023-04-03 15:23:32 +08:00
duzx16 4227999d4c No padding in colloator 2023-04-02 02:05:03 +08:00
duzx16 c508f62b70 Fix position_ids in prediction 2023-04-02 01:59:07 +08:00
duzx16 ca43864f39 Change quantization instruction 2023-04-02 00:36:14 +08:00
duzx16 4371f7a572 Add padding for evaluation data 2023-04-01 23:09:26 +08:00
duzx16 41a511ea06 Merge branch 'main' of github.com:THUDM/ChatGLM-6B 2023-04-01 19:49:06 +08:00
maybeluo 7a67ddd61f write generated result with utf-8 2023-04-01 00:34:19 +08:00
duzx16 7436f0840f Add todo 2023-03-31 22:55:36 +08:00
duzx16 ff3761fc1a Merge branch 'main' of github.com:THUDM/ChatGLM-6B 2023-03-31 20:15:51 +08:00
duzx16 73f4fe1ffe Add validation file name 
Use full prediction
 2023-03-31 20:15:35 +08:00
rainatam 893706a82d Update train script 2023-03-31 18:12:04 +08:00
duzx16 08d880141d Fix revision for loading model 2023-03-31 16:32:34 +08:00
duzx16 08f0731e94 Merge branch 'main' of github.com:THUDM/ChatGLM-6B 2023-03-31 15:19:16 +08:00
duzx16 c206e7d9ad Update requirements.txt 2023-03-31 15:18:21 +08:00
Aohan Zeng 9853cd2c97
Update README.md 2023-03-31 12:26:09 +08:00
Aohan Zeng 99875468dd
Update README.md 2023-03-31 11:46:21 +08:00
duzx16 24e24d5d6c Fix model path 2023-03-31 11:30:36 +08:00
duzx16 5e818065e4 Update memory requirement 2023-03-31 11:29:34 +08:00
duzx16 d2645d8816 Update batch size 2023-03-31 11:28:13 +08:00
duzx16 971a6fbb20 Updaet ADGEN link 2023-03-31 11:27:29 +08:00