Commit Graph

  • 4135e69406 fix flashattn + packing hiyouga 2024-07-21 17:07:45 +08:00
  • ad71296a7c update wechat hiyouga 2024-07-20 22:00:44 +08:00
  • 44e48e2b82 update deepseek template huangpan.foo 2024-07-19 15:02:54 +08:00
  • 88c7fc1599 set dev version hiyouga 2024-07-19 02:01:46 +08:00
  • 8f6995081c update parser hiyouga 2024-07-19 01:36:39 +08:00
  • bbd5a64423 release v0.8.3 hiyouga 2024-07-19 01:21:18 +08:00
  • cdb0f34f10 fix test hiyouga 2024-07-19 01:17:37 +08:00
  • e80006795f fix unittest hiyouga 2024-07-19 01:10:30 +08:00
  • 608de799a2 add unittest hiyouga 2024-07-19 01:06:27 +08:00
  • 779aae83d2 follow #4878 fix #4684 hiyouga 2024-07-18 22:06:12 +08:00
  • 2516763d69 Merge pull request #4878 from ly863/main hoshi-hiyouga 2024-07-18 22:03:41 +08:00
  • 1e7b396ff2 仅仅训练最后一轮对话 Shiyu Zhang 2024-07-18 15:30:25 +08:00
  • beec77a089 fix metrics #4786 hiyouga 2024-07-17 00:47:00 +08:00
  • d774b94f12 support batch_eval_metrics, fix #4826 hiyouga 2024-07-17 00:33:00 +08:00
  • bda302fbfb tiny fix hiyouga 2024-07-15 23:09:50 +08:00
  • f2aaebdbde Merge pull request #4822 from codemayq/test-ci hoshi-hiyouga 2024-07-15 23:07:55 +08:00
  • 10289eab15 Update test_template.py hoshi-hiyouga 2024-07-15 23:04:39 +08:00
  • da990f76b8 Update test_template.py hoshi-hiyouga 2024-07-15 23:00:27 +08:00
  • 38bc411d42 Merge pull request #4821 from codemayq/feature-eval-split hoshi-hiyouga 2024-07-15 22:59:44 +08:00
  • 91ba083f37 Update llama3_lora_eval.yaml hoshi-hiyouga 2024-07-15 22:55:12 +08:00
  • 33420bab81 Update test_template.py hoshi-hiyouga 2024-07-15 22:55:05 +08:00
  • 52a4256ad9 Update test_template.py hoshi-hiyouga 2024-07-15 22:52:25 +08:00
  • fd8cc49008 fix #4820 hiyouga 2024-07-15 22:32:07 +08:00
  • b0aa321a4a update wechat hiyouga 2024-07-15 22:02:52 +08:00
  • 32c3afdfa1 add IN_GITHUB_ACTIONS codingma 2024-07-15 10:28:07 +08:00
  • 645211dc01 1. change the task name format 2. delete split param in data_args.py codingma 2024-07-15 09:55:33 +08:00
  • 99ab7a8c1c allow computing rouge in training hiyouga 2024-07-15 01:16:26 +08:00
  • 29ebcd75d5 fix up hiyouga 2024-07-15 01:04:56 +08:00
  • 15b399a82f Merge pull request #4691 from codemayq/feature-suppot-eval-dataset hoshi-hiyouga 2024-07-15 01:00:34 +08:00
  • cba673f491 Update data_args.py hoshi-hiyouga 2024-07-15 00:56:03 +08:00
  • df52fb05b1 Update preprocess.py hoshi-hiyouga 2024-07-15 00:55:36 +08:00
  • 84e4047f8a Update parser.py hoshi-hiyouga 2024-07-15 00:55:21 +08:00
  • 97a0e291c7 Update data_utils.py hoshi-hiyouga 2024-07-15 00:54:34 +08:00
  • a5b809516e Update loader.py hoshi-hiyouga 2024-07-15 00:50:06 +08:00
  • a4ae3ab4ab update test template hiyouga 2024-07-15 00:49:34 +08:00
  • 3d39d74003 Update parser.py hoshi-hiyouga 2024-07-14 23:04:34 +08:00
  • 9d64507bd5 Update README.md hoshi-hiyouga 2024-07-14 21:27:04 +08:00
  • f1d8d29bc3 add gemma test hiyouga 2024-07-14 18:01:45 +08:00
  • 173921419d fix test hiyouga 2024-07-14 15:44:30 +08:00
  • 88a20ba797 fix #4699 hiyouga 2024-07-14 15:34:22 +08:00
  • d3c01552e0 tiny fix hiyouga 2024-07-14 10:56:45 +08:00
  • 2f6af73da2 fix gemma2 attention hiyouga 2024-07-13 23:33:45 +08:00
  • 7b19e99ed7 update workflows hiyouga 2024-07-13 22:31:15 +08:00
  • 5da54deb50 Merge pull request #4781 from hzhaoy/fix-dockerfile-cuda hoshi-hiyouga 2024-07-13 22:25:32 +08:00
  • 6b48308ef9 fix #4792 hiyouga 2024-07-13 22:07:58 +08:00
  • 32699a82a6 Merge pull request #4804 from codemayq/fix-examples hoshi-hiyouga 2024-07-13 20:49:13 +08:00
  • f618b80fa2 Update llava1_5.yaml hoshi-hiyouga 2024-07-13 20:30:06 +08:00
  • 982a1cdd24 1. fix output_dir in llama3_lora_pretrain.yaml 2. add llava1_5.yaml for inference codingma 2024-07-13 13:16:22 +08:00
  • 8bab99c582 tiny fix hzhaoy 2024-07-12 00:28:44 +08:00
  • 642c6d666f fix #4780 hzhaoy 2024-07-12 00:25:48 +08:00
  • a8bf1abf0f fix #4779 hzhaoy 2024-07-12 00:15:15 +08:00
  • 67040f149c update wechat_npu.jpg codemayq 2024-07-11 20:03:39 +08:00
  • 555194e150 Merge pull request #4700 from marko1616/patch-1 hoshi-hiyouga 2024-07-10 13:51:50 +08:00
  • 40c3b88b68 Merge pull request #4746 from yzoaim/fix hoshi-hiyouga 2024-07-10 13:32:49 +08:00
  • 39cd89ce17 Update callbacks.py hoshi-hiyouga 2024-07-10 13:32:20 +08:00
  • cff89a2e89 fix src/llamafactory/train/callbacks.py -.- 2024-07-10 12:05:51 +08:00
  • 51942acee8 fix #4731 hiyouga 2024-07-10 11:32:36 +08:00
  • fb0c400116 fix ppo trainer hiyouga 2024-07-10 11:05:45 +08:00
  • 2f09520c0d fix #4742 hiyouga 2024-07-09 23:24:24 +08:00
  • 86b1594823 Update wechat.jpg hiyouga 2024-07-09 09:25:11 +08:00
  • 563a27dab7 Merge pull request #4706 from T-Atlas/main hoshi-hiyouga 2024-07-07 15:50:38 +08:00
  • f84b007ebb Update packages.py hoshi-hiyouga 2024-07-07 15:48:29 +08:00
  • 322663bf90 chore: Update vllm_engine.py to support vllm version >= 0.5.1 Lian Junhong 2024-07-07 15:08:12 +08:00
  • a15782cb9f fix #4705 hiyouga 2024-07-07 13:10:06 +08:00
  • e0562521bb Update utils.py marko1616 2024-07-06 20:40:13 +08:00
  • 53b1002fb7 add codegeex4, internlm2.5 hiyouga 2024-07-06 16:16:47 +08:00
  • c9bb0757ec update pissa example hiyouga 2024-07-06 15:47:32 +08:00
  • 76f3bbcfc0 1. add custom eval dataset support 2. merge load dataset and split dataset function codingma 2024-07-05 15:52:10 +08:00
  • 9f33f1edf5 fix processors hiyouga 2024-07-05 08:33:22 +08:00
  • e43809bced fix #4683 hiyouga 2024-07-05 00:58:05 +08:00
  • ed232311e8 fix #4674 hiyouga 2024-07-05 00:41:03 +08:00
  • 226a9e563f Merge branch 'main' of https://github.com/hiyouga/LLaMA-Factory hiyouga 2024-07-04 14:23:37 +08:00
  • 1e27e8c776 fix #4677 hiyouga 2024-07-04 14:22:07 +08:00
  • 07d96d497c Merge pull request #4673 from hzhaoy/main hoshi-hiyouga 2024-07-04 10:40:41 +08:00
  • 738df47748 tiny fix hzhaoy 2024-07-04 10:20:28 +08:00
  • 636bb9c1e6 update tests hiyouga 2024-07-04 04:00:12 +08:00
  • 0c699de39d tiny fix hiyouga 2024-07-04 03:47:05 +08:00
  • 44747cebd2 tiny fix hiyouga 2024-07-04 03:02:23 +08:00
  • b5d101e1bf fix data map for packing hiyouga 2024-07-04 03:01:31 +08:00
  • b03e4a74ba update wechat hiyouga 2024-07-04 01:55:05 +08:00
  • 6fd6aa4530 fix packing for eager/sdpa attn hiyouga 2024-07-04 01:52:43 +08:00
  • 87d9b2d005 Merge pull request #4224 from chuan298/main hoshi-hiyouga 2024-07-04 01:18:54 +08:00
  • cce7083024 update packing hiyouga 2024-07-04 01:10:55 +08:00
  • a36e8f2dd5 Update packing.py hoshi-hiyouga 2024-07-03 23:36:01 +08:00
  • c346f79f99 update func name hiyouga 2024-07-03 23:29:33 +08:00
  • 8a6a7b9c8a update arg name hiyouga 2024-07-03 23:23:24 +08:00
  • 575a02a23d update hparams hiyouga 2024-07-03 23:18:58 +08:00
  • 7f770f6895 update ui hiyouga 2024-07-03 23:13:49 +08:00
  • a4a1ddbcb9 test hiyouga 2024-07-03 23:05:39 +08:00
  • 1e0c860c8c update scripts hiyouga 2024-07-03 20:07:44 +08:00
  • 8845e94f91 fix #4609 hiyouga 2024-07-03 19:45:51 +08:00
  • 87346c0946 update readme hiyouga 2024-07-03 19:39:05 +08:00
  • 3449c3531f Merge pull request #4662 from wzh1994/wzh/readme hoshi-hiyouga 2024-07-03 15:51:02 +08:00
  • 6f8f53f879 Update README_zh.md wangzhihong 2024-07-03 14:59:09 +08:00
  • 22da47ba27 add LazyLLM to Projects using LLaMA Factory in README.md wangzhihong 2024-07-03 11:12:20 +08:00
  • 8b1172b910 tiny fix hiyouga 2024-07-03 02:31:50 +08:00
  • 71cdf8956e tiny fix hiyouga 2024-07-02 23:06:13 +08:00
  • 821bb6660e remove rlhf support for chatglm2&3 hiyouga 2024-07-02 23:03:17 +08:00
  • c13ae2df19 upcast logits hiyouga 2024-07-02 22:32:05 +08:00
  • c47ab6c072 improve rlhf hiyouga 2024-07-02 22:23:08 +08:00