887 Commits

Author SHA1 Message Date
hiyouga
3e8c3b506a improve aligner
Former-commit-id: cc7296b92e10c24967fc753393275b71d300683f
2024-02-10 16:39:19 +08:00
hoshi-hiyouga
1bbdcca775 Merge pull request #2462 from mnmueller/main
Enable Parsing of SlimOrca

Former-commit-id: 99eed520b87152ca6b89c2a068b09200fd45f30d
2024-02-09 22:55:48 +08:00
hiyouga
6dde0508e9 improve fix tokenizer
Former-commit-id: 57b138abad6397596bc47be94e092e8fabedc06f
2024-02-09 14:53:14 +08:00
Mark Mueller
ac5d3811bd Slim Orca data parsing
Former-commit-id: f2d8efede7e20edafed0d5446eb64f2d419949b1
2024-02-08 19:32:20 +01:00
Mark Mueller
1440baa838 Slim Orca data parsing
Former-commit-id: ca57d27c39d4e7bc3dd7c3207a23d23d2cbd446b
2024-02-08 17:56:18 +01:00
Mark Mueller
68a0f2ae61 Slim Orca data parsing
Former-commit-id: 3016427be4e63fd25f40bc5a0d1f8cedc0997334
2024-02-08 17:54:18 +01:00
Mark Mueller
15f2b8baa3 Slim Orca data parsing
Former-commit-id: 4dca3907964d27abc2b21eb55c75676901c98912
2024-02-08 17:52:36 +01:00
Mark Mueller
a9a77a37f7 SlimOrca aligner
Former-commit-id: 928dda93867c2327a7957c04648592044ccf9daf
2024-02-08 08:28:32 -08:00
hoshi-hiyouga
4e20904d44 Merge pull request #2423 from mayflower/main
Support for german sft and dpo

Former-commit-id: 8e282e4e6bee6493b1bd38ba239ca49a6a840a92
2024-02-07 15:58:20 +08:00
Johann-Peter Hartmann
5a23651531 WS fix
Former-commit-id: 131935346ac06738be5e7c7f54fe2eb7d3769d7a
2024-02-06 20:13:04 +01:00
Johann-Peter Hartmann
66e1781ee9 add ranking to dpo dataset
Former-commit-id: 6a844fb384dd9cac3fd6b845a6b414320c5eb766
2024-02-06 20:12:36 +01:00
hiyouga
b14969ff4b Update tests.yml
Former-commit-id: c882b7cf339304ff16a36b1544a3b5f1194ef346
2024-02-07 01:18:22 +08:00
hiyouga
d4da4d55e4 lint
Former-commit-id: 6b1f89b6494e9b6b087fe90600617a3024e014e5
2024-02-07 01:10:04 +08:00
hiyouga
0ef64deae2 Update pyproject.toml
Former-commit-id: 650251ea77fae2e2595ca804f49efdd230dbb5b1
2024-02-07 00:45:58 +08:00
hiyouga
3c35a04280 update gc kwargs
Former-commit-id: 0cb81c156bc8c21a4bbdd3289a491f78dfcaf730
2024-02-07 00:38:24 +08:00
hiyouga
1a5edb7144 fix #2438
Former-commit-id: 412d856eeada2abcea598fac0a8d35ae90cc9c01
2024-02-06 15:23:08 +08:00
hiyouga
f5992681f7 add models
Former-commit-id: 0fdf61b2f765c125acda4f406eb25b3e59e75db2
2024-02-06 14:57:23 +08:00
hiyouga
2a6a0b7d4d support qwen1.5
Former-commit-id: 8a03a572b058c5cc4ff598670dc8595b2b97e374
2024-02-06 00:10:51 +08:00
hoshi-hiyouga
dbcf439354 fix #2436
Update test_toolcall.py

Former-commit-id: 39c539b6470c532ac639efbd2a1c485d2f5d485f
2024-02-05 22:55:28 +08:00
hoshi-hiyouga
f3247d9d70 Update test_toolcall.py
Former-commit-id: f50a684a9d6fc2351436d3d7020dc84bc1553a5d
2024-02-05 22:51:03 +08:00
hoshi-hiyouga
976786a391 Update test_toolcall.py
Former-commit-id: 97bcae546ab80737a906e5e28953f41b657f6c99
2024-02-05 22:50:43 +08:00
tao.jun
075cd83b25 Update test_toolcall.py
Add openai version notes

Former-commit-id: 9ea4ab214e64f73ec902e76b82fc42419571fd66
2024-02-05 20:49:23 +08:00
Johann-Peter Hartmann
623152d7d2 Merge branch 'hiyouga:main' into main
Former-commit-id: efbb0153981d0650f3a581e324b83054ca8063c1
2024-02-04 13:55:00 +00:00
hiyouga
e050204737 fix #2421
Former-commit-id: 43918c12310f7560d3820e5c6d72964309afeb8b
2024-02-04 21:02:55 +08:00
Johann-Peter Hartmann
7676ac5f5a Merge branch 'hiyouga:main' into main
Former-commit-id: 0395d0aafb69e86645e6b0a36b8f8dadb82219e0
2024-02-04 12:51:25 +00:00
hiyouga
274a61f39d fix reserved label len
Former-commit-id: b06d6c05a1911f329252a7572240048e456affdc
2024-02-04 17:54:26 +08:00
hiyouga
84ec6b5d01 fix #2420
Former-commit-id: 7a34087e4db62e603c9a9a26d8ff3910d7b10c40
2024-02-04 15:51:47 +08:00
hiyouga
f14cadf12d fix #2189
Former-commit-id: b3d81b229d376671e1c12229aeb487b0d84f2548
2024-02-04 00:47:37 +08:00
hiyouga
4adb4477bc bump up transformers version
Former-commit-id: 82f4d4301ed9f31b160d6313a1d2d44a22865f4d
2024-02-04 00:01:16 +08:00
hiyouga
dcca5901a6 fix #2397
Former-commit-id: 7404692808f2288d539668d364965ad104dacadb
2024-02-03 23:45:31 +08:00
hiyouga
80c0ad44a3 add hint for freeze #2412
Former-commit-id: 9600c93633629605573d908019563fa3870ad6f8
2024-02-03 23:38:56 +08:00
hiyouga
434e858c4e fix #2376
Former-commit-id: 8e2cfa7cca21b7fd4538d72114e36f704bcc82fe
2024-02-03 23:14:31 +08:00
hiyouga
fded83c00e support minicpm #2404
Former-commit-id: 4449e91cbee8fd804cf8bf1ff6b9f5301fde94ed
2024-02-03 22:36:46 +08:00
Johann-Peter Hartmann
d900ef1e23 add simple german chatml template chatml_de
Former-commit-id: 9f1d67c09f1af2c7aa383adec66842cacde92e33
2024-02-03 09:01:15 +01:00
Johann-Peter Hartmann
af258902c4 remove comma
Former-commit-id: 57a2f6d35da8cd10fad9859382bc1e983da56705
2024-02-03 08:48:39 +01:00
Johann-Peter Hartmann
c732a7ccfa Merge branch 'hiyouga:main' into main
Former-commit-id: c350237d891df7edd7e681f9da5ac1446fdeb568
2024-02-03 08:43:12 +01:00
hoshi-hiyouga
e5c9863f9a Merge pull request #2411 from lxsyz/main
fix eos_token_id=0 bug

Former-commit-id: 019a353e74ec70a9a2d8987df1ed19483413211a
2024-02-02 17:38:16 +08:00
Fallen Angel
e884171cd8 fix eos_token_id=0 bug
when eos_token_id=0, will never add eos_token

Former-commit-id: 576b4881c386d897462a875b28066ce9d6e06dd5
2024-02-02 17:34:48 +08:00
Johann-Peter Hartmann
17fbc73f4d Merge branch 'hiyouga:main' into main
Former-commit-id: 25b0a11c715f87812edba1ca14d3122a75f421de
2024-01-31 14:05:52 +01:00
hiyouga
38228d2d9f fix #2388
Former-commit-id: 203a36c9adfd9aa0f35fbf8089c9138534d68c53
2024-01-31 17:23:56 +08:00
hiyouga
7f28b961a5 fix autoset attn impl, update data readme
Former-commit-id: 34a6e5f82baf45cc8dbb11f9f7ab4a480ab7ec5c
2024-01-31 11:58:07 +08:00
Johann-Peter Hartmann
912bb5cb03 Add support for german datasets
Former-commit-id: bbc038aa236952597e97d1ccf1ae2d64a16339b5
2024-01-30 10:18:01 +01:00
hiyouga
eafdae8e94 fix #2320
Former-commit-id: e0b0c4415aaf80e75f6dd4f3777a0616b0e60f84
2024-01-24 16:19:18 +08:00
hoshi-hiyouga
71349f6696 Merge pull request #2319 from ftgreat/main
Add patch_mixtral_replace_moe_impl for full training Mitral using DeepSpeed Zero3

Former-commit-id: 0fadcd5f9deb9f03d341b6611c15f337f07e32d1
2024-01-24 15:32:26 +08:00
ldwang
d1a35c3fb1 Add patch_mixtral_replace_moe_impl for full training Mitral using DeepSpeed Zero3.
Signed-off-by: ldwang <ftgreat@gmail.com>

Former-commit-id: 5f50c02f0e425737cd80abdf8fde9e25abf13083
2024-01-24 15:25:31 +08:00
ldwang
0df7de7ab0 Add patch_mixtral_replace_moe_impl for full training Mitral using DeepSpeed Zero3.
Signed-off-by: ldwang <ftgreat@gmail.com>

Former-commit-id: d1413dcec8a3b1d671f240b82a689c72b54d7b93
2024-01-24 14:43:16 +08:00
hiyouga
fa9939b2b2 Update dataset_info.json
Former-commit-id: 4fe04ac7fc464c0ed705281cd3860839c18d6fc0
2024-01-23 00:10:32 +08:00
hiyouga
115e7af908 add hint
Former-commit-id: c540ef41bda61993b83ef8cfe3c84b1d169e984c
2024-01-22 23:32:01 +08:00
hoshi-hiyouga
7e27722cbb Merge pull request #2283 from A-Cepheus/main
fix: ZeRO3 does not work with MoE models
Former-commit-id: f5ea760abec2aac8d29ce5c945647be05648e676
2024-01-22 23:28:45 +08:00
hoshi-hiyouga
e3dfc7de11 Update patcher.py
Former-commit-id: 33556cc6b0b65cc6db02e66f4f6e75112c33d966
2024-01-22 23:27:39 +08:00