p04798526
/
LLaMA-Factory-Mirror
1
0
Fork 1
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Commit Graph

  • 20929444ff chore: add sort resutl py and 9g results main wql 2024-09-02 10:57:32 +0800
  • d6468734bc add: add results wql 2024-08-27 09:24:46 +0800
  • 1ed68086e9 chore: sort gpu status wql 2024-08-27 09:20:54 +0800
  • e0a10b6bee add: add chatglm inference results wql 2024-08-26 07:42:35 +0000
  • 7fbc470195 change: change for inference run wql 2024-08-26 15:04:31 +0800
  • f45e96825b train: add inference results wql 2024-08-26 06:44:32 +0000
  • 51faa7dda7 train: change date of gpu status wql 2024-08-26 12:10:47 +0800
  • dfbc8a2810 train: prepare batch run wql 2024-08-26 12:08:57 +0800
  • e434505c6b train: modify inference and add start end time wql 2024-08-26 12:06:23 +0800
  • 47b4cd3a54 del: del old results with backup wql 2024-08-26 11:58:08 +0800
  • 24f58972f3 del: del for more space with backups in my computer and add gpu status wql 2024-08-26 03:40:42 +0000
  • ffe5b77d7f change: change date for gpu status wql 2024-08-25 20:59:26 +0800
  • f59b530ee0 Merge branch 'main' of https://osredm.com/p04798526/LLaMA-Factory-Mirror wql 2024-08-24 21:47:34 +0800
  • 6f6a823085 add: add flash attn 2.0.8 wql 2024-08-24 21:44:00 +0800
  • 3594d14633 train: add step 500 result wql 2024-08-24 13:05:29 +0000
  • ded2b0e128 change: change gpu status date wql 2024-08-24 00:10:52 +0800
  • bffeeddf29 change: change for step500 run wql 2024-08-24 00:00:56 +0800
  • d5b1161eff train: add results wql 2024-08-23 13:54:33 +0000
  • 374496c370 chore: remove results/lore_sft wql 2024-08-23 10:11:32 +0000
  • bd3f48071c chore: del saves wql 2024-08-23 09:53:17 +0000
  • 64e456a9db chore: add gpu status wql 2024-08-23 09:38:47 +0000
  • b4525d409a chore: add saves in git ignore wql 2024-08-23 17:37:37 +0800
  • ffd1349660 add: add gpu status wql 2024-08-23 09:36:07 +0000
  • 140d7d533c train: prepare for batch run wql 2024-08-22 21:35:59 +0800
  • d217df9443 fix: fix small bug wql 2024-08-22 16:22:42 +0800
  • 72df1af06e feat: update gpu status code wql 2024-08-22 16:10:27 +0800
  • d4cea6f9ac chore: change yaml wql 2024-08-22 15:12:08 +0800
  • fdae778fa7 train: done test1 wql 2024-08-22 06:46:44 +0000
  • 7f5b10d654 chore: change yaml and git ignore wql 2024-08-22 13:27:24 +0800
  • c2b4a2db78 change: change test1 yaml wql 2024-08-22 13:21:55 +0800
  • 8eb67cb9f2 change: change yaml wql 2024-08-22 11:21:19 +0800
  • f47d38717f change: change test yaml wql 2024-08-22 11:09:58 +0800
  • 29a4e49dfe add: add test yaml wql 2024-08-22 10:46:22 +0800
  • 1c0f790c9b update: git ignore wql 2024-08-22 10:41:52 +0800
  • 1cae7dbe8a train: run baichuan once wql 2024-08-22 02:22:17 +0000
  • bfa2e166d7 change: new train yaml wql 2024-08-22 09:35:51 +0800
  • 429c1cd574 train: run qwen single once wql 2024-08-21 06:23:09 +0000
  • cf1107fbfa chore: add baichuan fix file wql 2024-08-21 13:44:02 +0800
  • bd971173c9 Merge branch 'main' of https://osredm.com/p04798526/LLaMA-Factory-Mirror wql 2024-08-21 13:15:59 +0800
  • 3fdf2cb71a chore: change model_name_or_path wql 2024-08-21 13:15:54 +0800
  • 4e55ae0a1a chore: include previous inference log wql 2024-08-21 02:52:31 +0000
  • 9525725e56 train: run llama and chatglm wql 2024-08-21 01:19:12 +0000
  • 83c41567b3 Merge branch 'main' of https://osredm.com/p04798526/LLaMA-Factory-Mirror wql 2024-08-20 17:39:26 +0800
  • 6e99c064ad change: gpu status wql 2024-08-20 17:38:32 +0800
  • 93c80971dc train: run chatglm wql 2024-08-20 09:32:46 +0000
  • 8793d13920 update: update gitignore wql 2024-08-20 17:31:35 +0800
  • 9411239d8d change: change for batch run wql 2024-08-20 17:25:47 +0800
  • af17ae5fb4 transfer: transfer chatglm file wql 2024-08-20 16:28:47 +0800
  • 40801b188c change: change yaml wql 2024-08-20 16:02:39 +0800
  • aa8eb9bff4 change: change yaml wql 2024-08-20 15:52:44 +0800
  • d8a730dcfe change: change yaml wql 2024-08-20 15:48:16 +0800
  • 07b328ee23 feat: add finish add log and gpu status wql 2024-08-20 14:31:29 +0800
  • abf6ab0743 Merge branch 'main' of https://osredm.com/p04798526/LLaMA-Factory-Mirror wql 2024-08-20 14:30:32 +0800
  • 0ae3f28774 test: test token and gpu status wql 2024-08-20 06:14:38 +0000
  • 39e97a5c5f Merge branch 'main' of https://osredm.com/p04798526/LLaMA-Factory-Mirror wql 2024-08-20 13:52:46 +0800
  • 0ab6f2836b feat: add cur_time to log wql 2024-08-20 10:35:46 +0800
  • 368a593cde Merge branch 'main' of https://osredm.com/p04798526/LLaMA-Factory-Mirror wql 2024-08-20 01:49:06 +0000
  • c93a5b8b8f add: add include_num_input_tokens_seen wql 2024-08-20 09:42:58 +0800
  • 36d18312d3 add: add test results wql 2024-08-19 09:12:34 +0000
  • d3f91c8e2f add: add test yaml wql 2024-08-19 16:29:03 +0800
  • 7f0b91db6b change: change yaml wql 2024-08-19 13:34:11 +0800
  • 25b8dd41f4 add: add test result wql 2024-08-19 05:08:37 +0000
  • d7d54df525 change: change batch run wql 2024-08-19 10:48:31 +0800
  • 7c5d56ca26 change: change yaml wql 2024-08-19 10:41:43 +0800
  • 3981d608f5 add: add max step 1000 result wql 2024-08-19 02:39:02 +0000
  • 746ceac74a train:test train wql 2024-08-19 09:57:13 +0800
  • 539d4d08f1 add: add results for llama2 lora and inference wql 2024-08-19 01:24:28 +0000
  • 40b5fec934 change: add comment wql 2024-08-18 23:54:18 +0800
  • f5b14a46be add: add batch run scripts wql 2024-08-18 14:02:58 +0800
  • a0569cadda test: test llama3 example wql 2024-08-18 11:11:07 +0800
  • 2469598eb4 chore: add help.txt wql 2024-08-16 11:04:18 +0000
  • 907282d2d7 add: inference result wql 2024-08-15 03:26:36 +0000
  • 0e8b03b638 change: change predict yaml wql 2024-08-15 11:18:12 +0800
  • c97367ad0a add: add predict yaml and chane old lora sft yaml wql 2024-08-15 11:05:49 +0800
  • 1190dfe2f2 add: add results wql 2024-08-15 01:41:12 +0000
  • 856bbeb6cc add: add results folder wql 2024-08-14 18:02:04 +0800
  • cfb01ac39e add: add flash-attn file wql 2024-08-14 16:31:14 +0800
  • faae9fa753 train: finish /train_24_8_13_13_16 wql 2024-08-13 06:20:31 +0000
  • beb97a099c train: change yaml wql 2024-08-13 13:19:42 +0800
  • 6f7bca808a train: add result of train_24_8_13_10_02/ wql 2024-08-13 03:24:35 +0000
  • f44393f413 train: change yaml wql 2024-08-13 10:05:16 +0800
  • 0841a0832f train: change yaml wql 2024-08-13 09:10:03 +0800
  • 2827dd1c98 train: finished /train_24_8_13_07_26/ wql 2024-08-13 01:05:14 +0000
  • dc953dd514 train: change lr wql 2024-08-13 07:36:30 +0800
  • 9fce0acb9b train: finish train /train_24_8_12_23_21 wql 2024-08-12 23:22:05 +0000
  • 14451dd6f1 train: train_24_8_12_23_21 wql 2024-08-12 23:27:42 +0800
  • 4b0b73c570 train: train_24_8_12_23_21 wql 2024-08-12 23:24:28 +0800
  • 4e88b01cd1 change: change para wql 2024-08-12 18:05:29 +0800
  • 65312954a1 change: change to en wql 2024-08-12 17:57:23 +0800
  • 4b61aafe34 add:train_24_8_12_16_4 wql 2024-08-12 09:44:49 +0000
  • 4d5b12487f fix: fix bug wql 2024-08-12 17:03:04 +0800
  • 41c42f67a2 change: change llama2_lora_sft.yaml wql 2024-08-12 16:51:45 +0800
  • 1ee249021b add: add train_24_8_12_15_46 wql 2024-08-12 08:13:14 +0000
  • 01f70612c7 change: change llama2_lora_sft.yaml dataset to alpaca_zh wql 2024-08-12 15:47:08 +0800
  • 90c6e4d020 fix: fix format wql 2024-08-12 15:42:18 +0800
  • d1718878af fix: rerun jsonl_to_json.py wql 2024-08-12 07:39:07 +0000
  • a8fe8b98dc update: update jsonl_to_json wql 2024-08-12 15:35:18 +0800
  • 0da139a06b add: add alpaca_zh.json wql 2024-08-12 07:26:30 +0000
  • 9698ef9781 add: add jsonl to json py script wql 2024-08-12 15:23:43 +0800
  • ce742cdb8f add: add jsonl file wql 2024-08-12 15:16:49 +0800