74 Commits

Author SHA1 Message Date
hiyouga
db42378f29 fix #3247
Former-commit-id: d1fb6c72b532bfd4ccd5b19f56708c8391fa53aa
2024-04-12 17:41:33 +08:00
hiyouga
2f878bde11 support ORPO
Former-commit-id: 17bf8a2c3a7bb5b83071c8659cfd8751e894e692
2024-03-31 18:29:50 +08:00
li.yunhao
0330ba2ae6 fix pile datset hf hub url
Former-commit-id: 9c2ef9cdf47e16985e07421b0bea414d161e2456
2024-03-30 16:06:10 +08:00
hiyouga
6646e18c02 add orca_dpo_pairs dataset
Former-commit-id: 3271af2afc90f10dcb101aeb9d7e4ef254d2dc0e
2024-03-20 20:09:06 +08:00
SirlyDreamer
78359638e3 Follow HF_ENDPOINT environment variable
Former-commit-id: e165965341a150f6faa2c072a9281ad99d7e5ce8
2024-03-20 08:31:30 +00:00
hiyouga
566bfad930 update parser
Former-commit-id: be99799413e1ba37807a02838bf2d87fd966bf55
2024-03-10 13:35:20 +08:00
hiyouga
9ae1514a75 update readme, add starcoder2, cosmopedia
Former-commit-id: 894d183214417b10af64d6add7be082d63e8b1f3
2024-03-03 01:01:46 +08:00
hiyouga
3b16912235 update data
Former-commit-id: 32884523c577f329354decb4c916bf1f1bbc9dff
2024-03-02 19:37:18 +08:00
hiyouga
7e2d8b170a fix #2533
Former-commit-id: 1630a4cb8f19a348014113421134b5730d52932f
2024-02-21 22:47:48 +08:00
hiyouga
62b78001b7 fix #2481
Former-commit-id: 22acab8aff8cadbba2a67e56af5701c0261ade49
2024-02-15 19:07:47 +08:00
hiyouga
9cf5d89bd1 update data/readme
Former-commit-id: a754f6e9ec157ba76178fa8ea8111e0c7b06008b
2024-02-10 21:04:29 +08:00
hiyouga
db2051684b improve aligner
Former-commit-id: 7d2dc83c5e2085da6273241269c9e9d7509ae51b
2024-02-10 16:39:19 +08:00
Mark Mueller
4bd7b8375e Slim Orca data parsing
Former-commit-id: 1d3598afa10797ba0ce30d44f52e7994587c0ce8
2024-02-08 19:32:20 +01:00
Johann-Peter Hartmann
ace1770085 WS fix
Former-commit-id: 49c69ea4b97a2507819996dea41a755a29e35e79
2024-02-06 20:13:04 +01:00
Johann-Peter Hartmann
6ff4e9e62c add ranking to dpo dataset
Former-commit-id: 1126563505924a2d7946fa3fad0d9d1756faf987
2024-02-06 20:12:36 +01:00
Johann-Peter Hartmann
77746ad86c remove comma
Former-commit-id: 870182c3a9ce3168db5b40a45daebe33c3d6f0e1
2024-02-03 08:48:39 +01:00
Johann-Peter Hartmann
81edbd1472 Merge branch 'hiyouga:main' into main
Former-commit-id: 4e27950acbfaef0ab6b4295d554c8897baedcff0
2024-01-31 14:05:52 +01:00
hiyouga
7beeae2209 fix autoset attn impl, update data readme
Former-commit-id: 521ad765521bb65aff5a29a8125a2b26ef00bff4
2024-01-31 11:58:07 +08:00
Johann-Peter Hartmann
c264eb4793 Add support for german datasets
Former-commit-id: d9a8301ed46d821c3303b14966978e1165d12f2c
2024-01-30 10:18:01 +01:00
hiyouga
cd4d38e0cc Update dataset_info.json
Former-commit-id: dbaaa4546ec681cfc84da015a67e2a9c79173e02
2024-01-23 00:10:32 +08:00
hiyouga
509e35ffc8 fix #2282 and update tool prompt
Former-commit-id: b2fb0eca56ee835438cc20e83f36ac3f6eb95c83
2024-01-22 22:27:30 +08:00
hiyouga
48cab43cb5 add array param format
Former-commit-id: 486cc8d3600397812e3927d43ab4181f4e86f5dd
2024-01-21 22:17:48 +08:00
hiyouga
e95c0242a8 fix dataset
Former-commit-id: 487dee066f51caea86dc65847bd326e13445de09
2024-01-18 12:59:30 +08:00
hiyouga
7f12aedc08 enable cutoff len
Former-commit-id: f1067d2b585cf24b3e48463692ac99a8222161c9
2024-01-18 12:25:42 +08:00
hiyouga
4e3bfb799d support function calling
Former-commit-id: d9f1cae35150cce594a7abd96dd2beb811fa33f2
2024-01-18 09:54:23 +08:00
hiyouga
a52aafdbdc tiny update
Former-commit-id: 5b93d545e2090d8d6db2cee3a047565f834e87f1
2023-12-25 18:29:34 +08:00
hiyouga
1af13cb737 add models
Former-commit-id: 709ac8870a17a96e786b32c75ad8c4e573148cee
2023-12-18 19:09:31 +08:00
hiyouga
f0f9d253d8 support autogptq in llama board #246
Former-commit-id: 71389be37cb0f1a65db6e501e11ca14e615c1a24
2023-12-16 16:31:30 +08:00
hiyouga
1a0bdd305c support system column #1765
Former-commit-id: 0a9c6e0146ebc71d5438c837463d6ab236e227c4
2023-12-12 19:45:59 +08:00
hiyouga
cefc0b2f03 fix modelscope data hub
Former-commit-id: d5b2c57a356539df9993e4774b856231eca8a6da
2023-12-12 18:33:06 +08:00
hoshi-hiyouga
b67085e13a Merge branch 'main' into feat/support_ms
Former-commit-id: 6382efec52f6be3daa5db0bd280a96162009fca1
2023-12-12 17:55:32 +08:00
xingjun.wang
e331e8c200 modify guanaco
Former-commit-id: e80a989d49366bf08f62d212d329a90a02d8167e
2023-12-12 15:00:37 +08:00
xingjun.wang
277790d868 update dataset info
Former-commit-id: 73b50a26b9c6282f28df87338fa4057759c38f69
2023-12-12 14:53:59 +08:00
xingjun.wang
879209829e update args for MsDataset.load
Former-commit-id: 09533e95edc5fa65a38b2f04c6d88506196021b3
2023-12-12 13:02:54 +08:00
xingjun.wang
9f17d36ccf add new datasets
Former-commit-id: fe4acc66b0e2bd96c988315192beb161da2d51f8
2023-12-12 12:44:15 +08:00
xingjun.wang
92fb73abd4 add open orca
Former-commit-id: 0ce18a378255a1d075a38a364520ba7a1e56180f
2023-12-12 12:34:04 +08:00
hiyouga
b641e9e97e fix #1784
Former-commit-id: 28d5de7e785f31b223a4646c9c1c770f43e187ec
2023-12-09 20:53:18 +08:00
yuze.zyz
9c30cdb53d fix typo
Former-commit-id: e4cf2a75caac75cb6320350ba179b8e2dcd87366
2023-12-08 18:13:26 +08:00
yuze.zyz
c523613f0a support ms dataset
Former-commit-id: 9c2247d700763f480d88a5dd46480cb32cfc174e
2023-12-08 18:00:57 +08:00
hiyouga
9a6b694e12 fix #1696
Former-commit-id: bf6f6aeefe65b4949633648b8711525c0029c001
2023-12-01 15:34:50 +08:00
Marco
a26f68ba47 Update dataset_info.json
Added the Nectar dataset already preprocessed and divided in sft and rl to which I added a preprompt to each instruction since it has been seen that this increase instruction following

Former-commit-id: 9468ee9012bfe7124fc5cc2acebcfe03a6d0cdee
2023-11-30 16:21:34 +01:00
hiyouga
303956cbb9 update dataset
Former-commit-id: 7b1aa6f63c79c0d9cb5249fdb0d6a5f9a04f36bd
2023-11-17 23:19:12 +08:00
hiyouga
f441932bd1 support full-parameter PPO
Former-commit-id: ce783036001397a20b0b4c5da2fea6d0c03389d2
2023-11-16 02:08:04 +08:00
hiyouga
38755bced7 add template, modify datasets
Former-commit-id: 386f590209e466b51c17a7ac8cee55fc3ce928d7
2023-11-09 15:53:23 +08:00
hiyouga
b2bf10661b update data readme
Former-commit-id: 2b5e33c338e6e8b10c4cbaa68ed26ef3b38ad5f9
2023-11-03 00:15:23 +08:00
hiyouga
a9db89a025 update data readme (zh)
Former-commit-id: cc8ffa10d877f5893f3940204e5bec6f3266559f
2023-11-02 23:42:49 +08:00
hiyouga
a1b0655457 support sharegpt format, add datasets
Former-commit-id: a8371724130db2fbd7273a480e2acb251e382aec
2023-11-02 23:10:04 +08:00
hiyouga
1cd0ea1f13 add MathInstruct dataset
Former-commit-id: 026af87e7fce091a0cda1afd6df3d6ab6189de9a
2023-09-13 22:30:14 +08:00
hiyouga
a4fd976048 refactor dataset_attr, add eos in pt, fix #757
Former-commit-id: a9d1fb72f791ae57a4d12f4e3a7e2abccf6a7077
2023-09-01 19:00:45 +08:00
codemayq
d9b9d9d1fe add ad gen dataset
Former-commit-id: 604f85487b46b3eb01b68cb2cc6535b7cb5527a7
2023-08-27 20:35:32 +08:00