p12475398
/
LLaMA-Factory-Mirror
forked from p04798526/LLaMA-Factory-Mirror
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
2,012 Commits 1 Branch 30 Tags 9.7 GiB
Commit Graph

1370 Commits

Author SHA1 Message Date
hiyouga 9020524418 fix PPO trainer #551 , update readme 2023-08-18 11:43:10 +08:00
hiyouga 58f13e22da update training resuming 2023-08-18 01:41:17 +08:00
hoshi-hiyouga 7252903245
Merge branch 'main' into main 2023-08-18 01:37:23 +08:00
hiyouga d125218cde support bf16 ppo #551 2023-08-18 00:40:32 +08:00
hiyouga 9f4c2adc9a fix ChatGLM2 ppo #527 #528 2023-08-18 00:34:59 +08:00
hiyouga be21fc83f9 fix generation bug #532 2023-08-17 22:21:34 +08:00
hiyouga b0ed0dec5e fix streaming in pt stage #548 #549 2023-08-17 17:59:26 +08:00
hiyouga 892fd39373 fix baichuan and intern template 2023-08-17 01:27:20 +08:00
hiyouga d9e62711a3 fix generation 2023-08-16 22:39:54 +08:00
hiyouga 7407d9daa1 fix system prompt 2023-08-16 01:35:52 +08:00
hiyouga 273135f595 fix baichuan template #481 2023-08-15 11:38:21 +08:00
hiyouga af6c011fcb fix ChatGLM RLHF 2023-08-15 11:19:20 +08:00
hiyouga 80b4053602 alert pad_token source 2023-08-15 00:07:56 +08:00
hiyouga 9d0f6214b6 update webui 2023-08-14 22:45:26 +08:00
hoshi-hiyouga adb0f186e9
Merge pull request #511 from hiyouga/feature-autoTemplate 
add template match and stage in webui
 2023-08-14 22:44:04 +08:00
codemayq 0bf892ff1a auto match template when change model_name 2023-08-14 20:56:05 +08:00
codemayq 79c68e5527 add template match and stage in webui 2023-08-14 20:42:59 +08:00
hiyouga d019956808 fix ChatGLM lm_head #494 2023-08-14 14:14:48 +08:00
hiyouga 20a29297b1 fix bug in webui 2023-08-14 11:38:42 +08:00
hiyouga ca08e5efd3 fix webui cache 2023-08-14 11:37:01 +08:00
hiyouga ec94274ca1 web UI integrating RLHF 2023-08-14 10:48:47 +08:00
hiyouga 2f2fd55d81 fix #480 2023-08-14 00:23:56 +08:00
hiyouga d69b1388e6 fix webui 2023-08-12 23:52:07 +08:00
hiyouga 9dc6a296e3 tiny fix 2023-08-12 22:02:43 +08:00
hiyouga 8545c11c45 fix rope scaling 2023-08-12 22:00:01 +08:00
hiyouga 1836c020c5 update readme 2023-08-12 21:00:11 +08:00
hiyouga fa940c17b8 support rope scaling, fix #475 #476 #478 2023-08-12 20:46:27 +08:00
codemayq 6bc8e9866d add sft script preview in webui 2023-08-12 13:53:55 +08:00
hiyouga dd51c24203 fix unusual output of 8bit models #278 #391 2023-08-12 00:25:29 +08:00
hiyouga a48cb0d474 Release v0.1.6 2023-08-11 23:25:57 +08:00
hiyouga d3844e97e3 add defaults 2023-08-11 13:56:26 +08:00
hiyouga d59f938959 fix stop word in baichuan template 2023-08-11 13:51:46 +08:00
hiyouga 9c6dd10514 fix baichuan template 2023-08-11 13:45:47 +08:00
hiyouga 3ec4351cfd support DPO training (2305.18290) 2023-08-11 03:02:53 +08:00
hoshi-hiyouga 685dae4eff
Merge pull request #451 from jovialchen/main 
huggingface login for projects must login while running
 2023-08-10 17:25:38 +08:00
hiyouga ad6e7c76c7 fix webui val size 2023-08-10 15:20:44 +08:00
jiongxuc 3e000c2b60 huggingface login for projects must login while running 2023-08-10 14:57:12 +08:00
hiyouga eb6e571cb7 fix template 2023-08-09 23:14:27 +08:00
hiyouga ac29f4d5f0 fix template 2023-08-09 23:10:20 +08:00
hiyouga d86ea314a1 support val set in streaming mode 2023-08-09 23:00:26 +08:00
hiyouga 572ea3bafb fix tokenizer 2023-08-09 17:52:15 +08:00
niuba 2ec68d3398 add last_checkpoint support 2023-08-09 16:39:27 +08:00
hiyouga df946e6949 fix sft trainer 2023-08-09 16:35:03 +08:00
hiyouga 39cd8b6989 fix rm #420, fix template #426, fix #423 2023-08-09 16:23:31 +08:00
hoshi-hiyouga 2d90685358
fix llama2 template 2023-08-09 00:58:27 +08:00
hoshi-hiyouga 32fa5e8d70
fix tokenizer 2023-08-09 00:54:54 +08:00
hiyouga 3a720aac66 update webui 2023-08-09 00:26:11 +08:00
hiyouga eecc4b2131 fix tokenizer #417 2023-08-08 23:59:41 +08:00
hiyouga caa0eda27d fix bug 2023-08-08 21:28:28 +08:00
hiyouga 4b841a6b35 fix bug 2023-08-08 17:55:55 +08:00
hiyouga a9980617f5 fix chatml template #408 2023-08-08 17:44:39 +08:00
hiyouga 5453b93db0 update args spec 2023-08-07 15:23:35 +08:00
hiyouga 20cf27976f update readme 2023-08-07 15:02:02 +08:00
hiyouga 081345baca fix #376 2023-08-07 13:58:59 +08:00
hiyouga 220175ab24 update trainer 2023-08-07 13:34:35 +08:00
hiyouga e21ae01356 fix qwen eos token 2023-08-06 13:31:17 +08:00
hiyouga 7f18d2a335 fix qwen tokenizer #361 2023-08-05 17:06:05 +08:00
hiyouga 1afa51c2fa fix template for tiktoken 2023-08-05 13:42:42 +08:00
hiyouga 53d95725c5 remove redundant code 2023-08-05 00:27:27 +08:00
hiyouga c183b3551d fix template 2023-08-05 00:25:00 +08:00
hiyouga e4a15f863c fix llama2 template 2023-08-05 00:07:54 +08:00
hiyouga d87c8fd8ab fix bos and eos token 2023-08-04 23:55:57 +08:00
hiyouga 8172ad1b5e fix encode 2023-08-04 23:27:55 +08:00
hiyouga b4852f9406 support chatml safe encoding 2023-08-04 23:14:28 +08:00
hiyouga 69744c17e8 support interleave probs 2023-08-04 21:27:35 +08:00
hiyouga d6b14658d4 fix webui export model 2023-08-04 14:20:27 +08:00
hiyouga a0173c427d fix mtloader 2023-08-03 19:29:02 +08:00
hiyouga ff98f1cba8 tiny fix 2023-08-03 17:42:28 +08:00
hiyouga 2780792754 fix qwen inference 2023-08-03 16:31:55 +08:00
hiyouga ea30da4794 fix qwen inference 2023-08-03 16:15:38 +08:00
hiyouga 87f8f830e2 support Qwen-7B, fix InternLM-7B inference 2023-08-03 15:53:32 +08:00
hiyouga 53d6dc396d update web demo 2023-08-03 13:28:28 +08:00
hiyouga e23a3a366c fix webui 2023-08-03 12:43:12 +08:00
hiyouga 08f180e788 modify code structure 2023-08-02 23:17:36 +08:00
hiyouga 1d8a1878ea fix PPO trainer 2023-08-02 19:10:23 +08:00
hiyouga b5ba87952a update ppo trainer 2023-08-02 18:46:41 +08:00
hiyouga 286f7be346 fix memory leak of PPO trainer 2023-08-02 17:41:34 +08:00
hiyouga c689857bbb release v0.1.5 2023-08-02 16:10:31 +08:00
YC Chen ca125da0eb [fix] Remove useless code 2023-08-02 14:35:35 +08:00
YC Chen 4323773089 [feature] Fix template of Llama2 to match the offical template 2023-08-02 14:10:15 +08:00
hiyouga 968ce0dcce fix bug in preprocessing 2023-08-02 01:10:28 +08:00
hiyouga e3f80774c4 fix #296 2023-08-01 18:43:53 +08:00
hiyouga e6a3894b99 Fix #294 2023-08-01 18:13:03 +08:00
hiyouga befaab5720 fix webui 2023-08-01 12:11:37 +08:00
hiyouga ac88ce5233 fix RM save model 2023-08-01 11:56:17 +08:00
hiyouga 973a638665 release v0.1.4 2023-08-01 10:08:47 +08:00
hiyouga d3a0692d4d fix inference 2023-08-01 00:06:48 +08:00
hiyouga 9cb1f119a4 fix arg check 2023-07-31 23:48:57 +08:00
hiyouga 62dca5bb82 update readme 2023-07-31 23:42:32 +08:00
hiyouga 0411a4b3e1 support streaming data, fix #284 #274 #268 2023-07-31 23:33:00 +08:00
hiyouga 513e1f1ec9 Update data_args.py 2023-07-28 17:42:41 +08:00
hiyouga 91dd17d8a6 fix #268 2023-07-28 17:02:26 +08:00
hiyouga 00efa8a07f fix #242 2023-07-25 17:04:02 +08:00
hiyouga 035c966d5c update readme, fix web ui postprocess 2023-07-22 14:29:22 +08:00
NULL 7007fbc0b6
Merge branch 'hiyouga:main' into main 2023-07-21 17:00:26 +08:00
mrhan1993 9f0b57b370 根据GLM Efficient Tuning添加中文README，web添加了server_port 2023-07-21 16:57:58 +08:00
hiyouga 0b6150bc31 release v0.1.3 2023-07-21 16:48:34 +08:00
hiyouga d2f18197e3 fix save function 2023-07-21 14:09:07 +08:00
hiyouga 1d1d8538c9 Update runner.py 2023-07-21 13:35:19 +08:00
hiyouga ed0e186a13 update web UI, support rm predict #210 2023-07-21 13:27:27 +08:00
hiyouga 4c45a3a884 release v0.1.2 2023-07-20 22:33:59 +08:00
hiyouga 8333795fcb fix api 2023-07-20 22:14:54 +08:00
hoshi-hiyouga 6022adb72e
Merge pull request #213 from Ehco1996/patch-1 
feat: support pass args before init web app
 2023-07-20 22:12:07 +08:00
hiyouga 4d1641c1bf update UI, fix #212 2023-07-20 22:09:06 +08:00
Ehco b2874a72e4
feat: support pass args before init web app 
as title
 2023-07-20 21:49:26 +08:00
hiyouga 67a2773074 simplify code 2023-07-20 15:08:57 +08:00
hiyouga d1d8e8bae1 tiny fix 2023-07-19 22:53:46 +08:00
hiyouga d111e658a2 fix #199 2023-07-19 22:51:29 +08:00
hiyouga 7159bc54ed add datasets 2023-07-19 20:59:15 +08:00
hiyouga 925a790bc9 fix #196 2023-07-19 17:35:38 +08:00
hiyouga 8f7819fcaa fix #194 2023-07-19 17:07:33 +08:00
hiyouga 7a3ade8c69 support LLaMA-2 2023-07-19 16:42:14 +08:00
hiyouga 38eb1aaf55 add LLaMA2 template 2023-07-19 00:44:49 +08:00
hiyouga 29af67b015 fix API 2023-07-19 00:01:14 +08:00
hiyouga fe2887ca13 support dev set in web ui 2023-07-18 20:40:49 +08:00
hiyouga b447fa85aa add web demo 2023-07-18 17:21:16 +08:00
hiyouga bdf91846da update baichuan template 2023-07-18 16:43:51 +08:00
hiyouga d1ae428c6e fix template 2023-07-18 16:37:23 +08:00
hiyouga cadeac0f44 fix #176 2023-07-18 16:36:24 +08:00
hiyouga 6f9360c0bd fix webUI, fix #171 #177 2023-07-18 15:51:48 +08:00
hiyouga 12d8a8633f update webUI, fix #179 2023-07-18 15:35:17 +08:00
hiyouga b9fe83fb75 tiny fix 2023-07-18 00:52:31 +08:00
hiyouga 262252d67b a monkey patch for lora_target 2023-07-18 00:31:40 +08:00
hiyouga f8193e8009 release v0.1.0 2023-07-18 00:18:25 +08:00
hiyouga 85c2210452 fix #175 2023-07-17 18:07:17 +08:00
hiyouga 1e1358431d fix saving custom code 2023-07-16 18:04:41 +08:00
hiyouga 552d773dad fix callback 2023-07-15 22:01:43 +08:00
hiyouga 8528a84e74 update stream_chat 2023-07-15 19:51:02 +08:00
hiyouga 657cf0f55a create chat model 2023-07-15 19:26:20 +08:00
hiyouga d640c5545f Update callbacks.py 2023-07-15 17:39:16 +08:00
hiyouga 22d9a9c2af fix callback 2023-07-15 17:18:16 +08:00
hiyouga f751376613 modity code structure 2023-07-15 16:54:28 +08:00
hiyouga c30db9f1f0 fix eval and pred loss 2023-07-14 13:11:57 +08:00
hiyouga a04115ec27 fix pretrain 2023-07-13 23:41:54 +08:00
hiyouga 08439d29b2 fix Baichuan-13B 2023-07-13 23:08:45 +08:00
Jinghuan Shang dc1e8b7181
Fix typo in common.py 
lastest -> latest
 2023-07-11 18:03:53 -04:00
hiyouga b2f7cb4465 fix sft encode 2023-07-11 19:50:33 +08:00
hiyouga 1af031c02b add baichuan template 2023-07-11 18:57:50 +08:00
hiyouga 84a06318d4 update api to match langchain 2023-07-07 20:35:39 +08:00
hiyouga a2f507c562 support InternLM 2023-07-07 11:02:28 +08:00
hiyouga caa00d3ac2 fix rouge score 2023-07-06 14:28:34 +08:00
hiyouga 4abd2485e1 fix streaming response in API 2023-07-05 22:42:31 +08:00
hiyouga e6603977f6 fix freeze tuning 2023-07-05 21:18:28 +08:00
hiyouga a2ba69183b fix bug in PPO stage 2023-07-05 19:14:10 +08:00
hiyouga 8e3540c62d fix compute dtype 2023-07-05 15:13:00 +08:00
hiyouga c136f362c1 support falcon model #72 2023-07-05 15:00:06 +08:00
hiyouga cac87fd553 fix bleu score 2023-07-05 00:11:21 +08:00
hiyouga 395ed1cf1b set use_cache before saving model 2023-07-04 23:18:20 +08:00
hiyouga 65e9ce2cdd fix seq2seq predictions 2023-07-04 22:56:51 +08:00
hiyouga 92fa515e97 fix typo 2023-06-30 10:09:59 +08:00
hiyouga 4d0fddba21 update loading logic 2023-06-28 12:07:16 +08:00
hiyouga 0a46313cca fix loading best model 2023-06-28 01:55:12 +08:00
hiyouga 7826a8ca77 fix RM accuracy 2023-06-28 01:40:13 +08:00
hiyouga 450910c1db tiny fix 2023-06-27 23:54:24 +08:00
hiyouga 18f87c1b25 fix initializing data arguments 2023-06-27 22:50:23 +08:00
hiyouga 2e01abfda5 support save full model, replace BOS token 2023-06-27 21:40:11 +08:00
hiyouga 1c732e2537 fix decoding in seq2seq 2023-06-27 19:33:08 +08:00
hiyouga 1175948029 fix generation in seq2seq.py 2023-06-26 18:07:06 +08:00
hiyouga cec9760eb8 support prefixes, loading multiple local files 2023-06-26 15:32:40 +08:00
hiyouga f030b09924 update api 2023-06-26 13:39:57 +08:00
hiyouga 0697643358 update readme 2023-06-23 00:17:05 +08:00
hiyouga 614d3a996c update API 2023-06-22 20:46:24 +08:00
hiyouga 76ecb8c222 match api with OpenAI format 2023-06-22 20:27:00 +08:00
Bun 6e4db0903f Compatible with OpenAI API. 2023-06-21 14:45:04 +08:00
hiyouga f621f7631a add default template 2023-06-16 21:12:17 +08:00
hiyouga a6c4b141cd fix freeze layers 2023-06-16 17:38:21 +08:00
hiyouga fc4d8155b3 add source prefix 2023-06-16 16:32:17 +08:00
hiyouga 0574b590ef support loading lora from hub 2023-06-16 00:02:17 +08:00
hiyouga 0cee6ad67f support baichuan model 2023-06-15 16:02:01 +08:00
hiyouga c527399424 fix bug in template vanilla 2023-06-15 14:36:55 +08:00
hiyouga d668f8b501 add BOS token in pre-training 2023-06-15 01:46:17 +08:00
hiyouga b6faf0207d support multiturn training like FastChat 2023-06-14 22:27:39 +08:00
hiyouga 875e8e2349 fix loading valuehead 2023-06-13 11:13:06 +08:00
hiyouga 531a3764d9 fix generating args 2023-06-13 01:33:56 +08:00
hiyouga cec6524d6b support RM metrics, add generating Args 2023-06-12 15:48:48 +08:00
BUAADreamer a2af9df5a9 add code for reading from multi files in one directory 2023-06-10 16:27:30 +08:00
BUAADreamer 3dd5f9a874 add code for reading from multi files in one directory 2023-06-10 15:53:47 +08:00
hiyouga 2ba5d69c7f tiny fix 2023-06-07 16:42:31 +08:00
hiyouga 16c2860d56 tiny fix 2023-06-07 16:02:07 +08:00
hiyouga edafb97733 tiny fix 2023-06-07 12:58:14 +08:00
hiyouga 3875b19a34 add templates 2023-06-07 12:40:44 +08:00
hiyouga 17acf3a3eb add belle template 2023-06-07 12:30:11 +08:00
hiyouga ce43386080 tiny fix 2023-06-07 12:08:39 +08:00
hiyouga 909af8f496 add prompt template class 2023-06-07 11:55:25 +08:00
hiyouga 5d021d4ad5 fix inference, add prompt template 2023-06-07 10:52:35 +08:00
hiyouga 13d1f0709c recover logging 2023-06-06 21:36:37 +08:00
hiyouga 4eb17bcf6c support distributed quantized training 2023-06-06 17:39:41 +08:00
hiyouga 3d8d5ee5d5 add API demo from #1 2023-06-05 21:32:18 +08:00
hoshi-hiyouga 06e1b120e1
Merge pull request #11 from hiyouga/api 
Api
 2023-06-05 20:58:02 +08:00
hiyouga a38d57ddd7 fix bug in web demo 2023-06-05 17:58:29 +08:00
hiyouga 56eb99106a increase max length in cli demo 2023-06-05 16:49:14 +08:00
hiyouga fe1d930816 implement stream generating 2023-06-05 16:43:44 +08:00
hiyouga 44298c1235 tiny fix 2023-06-05 15:25:22 +08:00
hiyouga 38b83533a4 tiny fix 2023-06-04 16:35:50 +08:00
hiyouga eac9921e5c tiny fix 2023-06-04 12:55:40 +08:00
hiyouga 3b9eee8cd2 support QLoRA 2023-06-04 00:08:56 +08:00
hiyouga 1bd13d7ca1 fix int8 inference 2023-06-03 23:22:05 +08:00
hiyouga 926291940d reduce repetition penalty 2023-06-03 21:57:39 +08:00
hiyouga 0f69a0c19e fix int8 inference 2023-06-03 21:17:47 +08:00
hiyouga de09ee1315 add ziya prompt template 2023-06-03 19:05:51 +08:00
hiyouga 771f454ff1 use low_cpu_mem_usage to speed up loading 2023-06-03 18:19:01 +08:00
hiyouga dca27b4412 add logits processor 2023-06-03 16:34:54 +08:00
hiyouga ed6161fa6a remove unused code 2023-06-03 00:10:54 +08:00
hiyouga b8a034807e tiny fix 2023-06-02 19:02:25 +08:00
hiyouga e3aaef7d4a fix layer norm name in PPO 2023-06-02 17:30:01 +08:00
hiyouga bd565af370 fix #1 2023-06-02 14:25:00 +08:00
hiyouga 50d9a20f81 alter rewards data type 2023-06-02 14:19:51 +08:00
hiyouga e6126244c1 fix possibly OOM error 2023-06-01 23:54:44 +08:00
hiyouga fd709eacff fix bug at inference 2023-05-31 18:11:53 +08:00
hiyouga 740a5daf56 support BLOOM models 2023-05-31 16:54:06 +08:00
hoshi-hiyouga c36620ece4
Merge pull request #1 from mMrBun/main 
Support conversation via API.
 2023-05-30 16:34:00 +08:00
hiyouga a72492e649 remove dummy code 2023-05-30 16:28:00 +08:00
mMrBun 748b804bac Support conversation via API. 2023-05-30 15:00:28 +08:00
mMrBun e821682430 Support conversation via API. 2023-05-30 14:46:22 +08:00
hiyouga 8ff96509fa add pre-training script 2023-05-29 21:37:22 +08:00
hiyouga c0e5df92d6 fix checkpoint loading 2023-05-29 17:43:16 +08:00
hiyouga ce71cc8b6d tiny fix 2023-05-29 09:42:29 +08:00
hiyouga 166c837b95 tiny fix 2023-05-28 21:48:33 +08:00
hiyouga 0c9fda01e3 use fp16 model, add logcallback 2023-05-28 21:30:28 +08:00
hiyouga 769c6ab56b Initial commit 2023-05-28 18:09:04 +08:00