1916 Commits

Author SHA1 Message Date
hoshi-hiyouga
490c0dd3c0 fix #4917
Former-commit-id: e26919aafd8436489d065789c9c25d72c8d05a6d
2024-07-22 11:28:31 +08:00
hiyouga
a1947fc0b8 tiny fix
Former-commit-id: 9133316e558a3c8744f5eb6ab8678686bf4859ed
2024-07-22 00:06:03 +08:00
hiyouga
9aa1093362 fix flashattn + packing
Former-commit-id: 4adc6ce4abc718c25f39b316bfc3352d0d01ed1e
2024-07-21 17:07:45 +08:00
huangpan.foo
d72e3a2f01 update deepseek template
Former-commit-id: f5ca86ec95bb301df42ffaa6923fc3037a224e34
2024-07-19 15:02:54 +08:00
hiyouga
eacf4ecfb0 set dev version
Former-commit-id: 0b9a2275dc533b65578278f979ce053e95a644b3
2024-07-19 02:01:46 +08:00
hiyouga
8dfe34e307 update parser
Former-commit-id: 5262c8702382ff8bc36a172387bc4c8949f326ea
2024-07-19 01:36:39 +08:00
hiyouga
1b48a6c4f8 release v0.8.3
Former-commit-id: 7180a3b99c3c218dfb0dc607ad5e87219269a678
2024-07-19 01:21:18 +08:00
hiyouga
684a9a0b3c fix test
Former-commit-id: e86f20134b782c8f5c39ead292f8f7582038eb9e
2024-07-19 01:17:37 +08:00
hiyouga
bc7d92e08d fix unittest
Former-commit-id: 73b56ba30b17a32db694d485135d493315293001
2024-07-19 01:10:30 +08:00
hiyouga
a66ff6052b add unittest
Former-commit-id: 8a1f0c5f922989e08a19c65de0b2c4afd2a5771f
2024-07-19 01:06:27 +08:00
hiyouga
9573799224 follow #4878 fix #4684
Former-commit-id: 4715e5c5b8040b21e5f401f7e969b9fd2757d520
2024-07-18 22:06:12 +08:00
hoshi-hiyouga
cf96e7024c Merge pull request #4878 from ly863/main
Train the last turing conversation.

Former-commit-id: 1fd39b234e23f762021212c6dfde9701f94e7afa
2024-07-18 22:03:41 +08:00
Shiyu Zhang
1538923eed 仅仅训练最后一轮对话
Former-commit-id: ab6198e4c099edeb1a400f58729cd617e8cd8e50
2024-07-18 15:30:25 +08:00
hiyouga
6b16da0cd1 fix metrics #4786
Former-commit-id: 7d0c4bd394fc3cba197db1719f1164b9dd66ac21
2024-07-17 00:47:00 +08:00
hiyouga
746e9b352e support batch_eval_metrics, fix #4826
Former-commit-id: 3fe1df17188825f8a32fbe6a1294b4b532ce0c85
2024-07-17 00:33:00 +08:00
hiyouga
22995af79a tiny fix
Former-commit-id: 952807b16cd85fa193a05a83b1a735a6b06abc82
2024-07-15 23:09:50 +08:00
hoshi-hiyouga
be7aebd2b9 Merge pull request #4822 from codemayq/test-ci
add github action check to ignore some test cases

Former-commit-id: cf698aa7ab4a35b84f429014c4a5a6cb78b565a6
2024-07-15 23:07:55 +08:00
hoshi-hiyouga
2e4b2ed1aa Update test_template.py
Former-commit-id: 470dd92f954a06939d83557fed1201632b0c966b
2024-07-15 23:04:39 +08:00
hoshi-hiyouga
b024682d80 Update test_template.py
Former-commit-id: 7da56ea6d4c08d555e179d419c245b27e5611b97
2024-07-15 23:00:27 +08:00
hoshi-hiyouga
e2404a49d0 Merge pull request #4821 from codemayq/feature-eval-split
add "split" as suffix in eval task name

Former-commit-id: 5b6033eef3c2cfd5b47bb67e0d803d8de68f3ff0
2024-07-15 22:59:44 +08:00
hoshi-hiyouga
bc72f916af Update llama3_lora_eval.yaml
Former-commit-id: 946836f9a3f3385c8d3bc6ab82df6edf13ee571c
2024-07-15 22:55:12 +08:00
hoshi-hiyouga
9d22c68776 Update test_template.py
Former-commit-id: 352afce20adf26f5e616e5aa4e6c7295a865fb1a
2024-07-15 22:55:05 +08:00
hoshi-hiyouga
e6b9a7f2e1 Update test_template.py
Former-commit-id: 0ada82c60ed3df637acc624e8a382765d4c5f743
2024-07-15 22:52:25 +08:00
hiyouga
473b77f6a0 fix #4820
Former-commit-id: 8c0f8357e1eebee32010fe715554f1136b68b4ba
2024-07-15 22:32:07 +08:00
codingma
cd25bc5c6e add IN_GITHUB_ACTIONS
Former-commit-id: 3681966a3fe37a1c3d2dd60e54047ced1b2925e5
2024-07-15 10:28:07 +08:00
codingma
bfadfdd27b 1. change the task name format
2. delete split param in data_args.py


Former-commit-id: 309d30efe24785912ff751fc573677875fc5819e
2024-07-15 09:55:33 +08:00
hiyouga
392ac88d78 allow computing rouge in training
Former-commit-id: ac67d50673989e8137965f5f718fec67c184f55b
2024-07-15 01:16:26 +08:00
hiyouga
8ce43766c6 fix up
Former-commit-id: 43a56cb331fae899ca35b0c312730d4ab79d0c42
2024-07-15 01:04:56 +08:00
hoshi-hiyouga
07ea5796e5 Merge pull request #4691 from codemayq/feature-suppot-eval-dataset
add eval dataset support

Former-commit-id: 51eb379b44fad0336fc96c329ec98dc4528b9c2c
2024-07-15 01:00:34 +08:00
hoshi-hiyouga
9f16e33570 Update data_args.py
Former-commit-id: c3cee10294d56a1bc226871819b3a725b09aa67e
2024-07-15 00:56:03 +08:00
hoshi-hiyouga
3cf18efeef Update preprocess.py
Former-commit-id: da92f4a1b9c12a8e2489b964baba5e2c8e739ef1
2024-07-15 00:55:36 +08:00
hoshi-hiyouga
51265f81e7 Update parser.py
Former-commit-id: 145687997c86b8785e37dd60fbb9f3a5986730a6
2024-07-15 00:55:21 +08:00
hoshi-hiyouga
1e47c4a9d0 Update data_utils.py
Former-commit-id: 5c2a0e3b1d1afd2a9219d935d3421fffffc3a2c9
2024-07-15 00:54:34 +08:00
hoshi-hiyouga
f78cd9f9da Update loader.py
Former-commit-id: 860e3eb374947b72dcae88cab0a93ef561e3bfb3
2024-07-15 00:50:06 +08:00
hiyouga
8d1d5334dc update test template
Former-commit-id: 3cbd0739e8b889ef58a7841959a15b6cd1cb6332
2024-07-15 00:49:34 +08:00
hoshi-hiyouga
6978a9838f Update parser.py
Former-commit-id: b9760df588e64270a140d9111241c62c1cefe781
2024-07-14 23:04:34 +08:00
hoshi-hiyouga
de1efaed1f Update README.md
Former-commit-id: d9aa6a9437994ac29f3e7a0789ec286f091847d6
2024-07-14 21:27:04 +08:00
hiyouga
055b1b1744 add gemma test
Former-commit-id: f29d9f8665021e506d6237f5337d2b1ac8ede6a8
2024-07-14 18:01:45 +08:00
hiyouga
2de774fbaa fix test
Former-commit-id: 4899309b7cac00573215f6530bfc97d7d87d70b2
2024-07-14 15:44:30 +08:00
hiyouga
95f47490f9 fix #4699
slow tokenizer for yi models


Former-commit-id: 4d23a0bcda0c15a903a62eec72d14c584ce020dd
2024-07-14 15:34:22 +08:00
hiyouga
71275c49f8 tiny fix
Former-commit-id: 220d7c1ce15e8013a900e59fe0c7937e38b5c3b5
2024-07-14 10:56:45 +08:00
hiyouga
9cd850c3b9 fix gemma2 attention
Former-commit-id: aeafc68e169ae0ea5939cc81cb0cf89f0ca044b6
2024-07-13 23:33:45 +08:00
hiyouga
37c075de1c update workflows
Former-commit-id: 47c806da4def1694fb30c1c4cf87ae67903eb9f1
2024-07-13 22:31:15 +08:00
hoshi-hiyouga
3f6feba1ff Merge pull request #4781 from hzhaoy/fix-dockerfile-cuda
Fix cuda Dockerfile

Former-commit-id: 56696f6c112f82d514dc3bf93182707297642639
2024-07-13 22:25:32 +08:00
hiyouga
0a56404dd2 fix #4792
Former-commit-id: d7547d6b9e4c660897e3ce0f4022e08686c172d5
2024-07-13 22:07:58 +08:00
hoshi-hiyouga
8af0253ac0 Merge pull request #4804 from codemayq/fix-examples
tiny fix of examples

Former-commit-id: 1e45486a57a4c559e7deedf077acc0b5b79d631f
2024-07-13 20:49:13 +08:00
hoshi-hiyouga
4492c02647 Update llava1_5.yaml
Former-commit-id: 68c9670be5a6f9d9ec589f13b43c45aa0ed90033
2024-07-13 20:30:06 +08:00
codingma
ae0b844f2d 1. fix output_dir in llama3_lora_pretrain.yaml
2. add llava1_5.yaml for inference


Former-commit-id: 560928ecf04b7aa351812568d317fcde58bc64d6
2024-07-13 13:16:22 +08:00
hzhaoy
7043219f00 tiny fix
Former-commit-id: 48be67c41eb394d276b41ca22b28e1ef10af4920
2024-07-12 00:28:44 +08:00
hzhaoy
029ff815ec fix #4780
Former-commit-id: 15f73c41d556c5f8d989697d774725a88d36f1b4
2024-07-12 00:25:48 +08:00