Mark Mueller
|
08967e324a
|
Slim Orca data parsing
Former-commit-id: 7f792dfede
|
2024-02-08 17:54:18 +01:00 |
|
Mark Mueller
|
16d0bf0317
|
Slim Orca data parsing
Former-commit-id: 8bd4182609
|
2024-02-08 17:52:36 +01:00 |
|
Mark Mueller
|
842b56666a
|
SlimOrca aligner
Former-commit-id: 36d7a75966
|
2024-02-08 08:28:32 -08:00 |
|
hoshi-hiyouga
|
186ba72d72
|
Merge pull request #2423 from mayflower/main
Support for german sft and dpo
Former-commit-id: d0daaa01f9
|
2024-02-07 15:58:20 +08:00 |
|
Johann-Peter Hartmann
|
ace1770085
|
WS fix
Former-commit-id: 49c69ea4b9
|
2024-02-06 20:13:04 +01:00 |
|
Johann-Peter Hartmann
|
6ff4e9e62c
|
add ranking to dpo dataset
Former-commit-id: 1126563505
|
2024-02-06 20:12:36 +01:00 |
|
hiyouga
|
b20ecce773
|
Update tests.yml
Former-commit-id: d6775c6522
|
2024-02-07 01:18:22 +08:00 |
|
hiyouga
|
23dd337ac2
|
lint
Former-commit-id: 88a1bc9773
|
2024-02-07 01:10:04 +08:00 |
|
hiyouga
|
ced910b3f8
|
Update pyproject.toml
Former-commit-id: aacc823b0f
|
2024-02-07 00:45:58 +08:00 |
|
hiyouga
|
bbe5ff0570
|
update gc kwargs
Former-commit-id: 0ae9a16b9d
|
2024-02-07 00:38:24 +08:00 |
|
hiyouga
|
caeffc780d
|
fix #2438
Former-commit-id: ebf31b62eb
|
2024-02-06 15:23:08 +08:00 |
|
hiyouga
|
9debd64cef
|
add models
Former-commit-id: 85622ae757
|
2024-02-06 14:57:23 +08:00 |
|
hiyouga
|
dcfb9b5cfa
|
support qwen1.5
Former-commit-id: ccabb5b04a
|
2024-02-06 00:10:51 +08:00 |
|
hoshi-hiyouga
|
f45ed52161
|
fix #2436
Update test_toolcall.py
Former-commit-id: 7f48c599eb
|
2024-02-05 22:55:28 +08:00 |
|
hoshi-hiyouga
|
ac89ec9ced
|
Update test_toolcall.py
Former-commit-id: b5007afb19
|
2024-02-05 22:51:03 +08:00 |
|
hoshi-hiyouga
|
e3e7b4dc33
|
Update test_toolcall.py
Former-commit-id: d4994235f0
|
2024-02-05 22:50:43 +08:00 |
|
tao.jun
|
cb1a7e5b6b
|
Update test_toolcall.py
Add openai version notes
Former-commit-id: 4081c88723
|
2024-02-05 20:49:23 +08:00 |
|
Johann-Peter Hartmann
|
e7ff724a83
|
Merge branch 'hiyouga:main' into main
Former-commit-id: 1ecea9de63
|
2024-02-04 13:55:00 +00:00 |
|
hiyouga
|
d296e56fe9
|
fix #2421
Former-commit-id: 3dc86c4af9
|
2024-02-04 21:02:55 +08:00 |
|
Johann-Peter Hartmann
|
eb45057257
|
Merge branch 'hiyouga:main' into main
Former-commit-id: 63da6294dd
|
2024-02-04 12:51:25 +00:00 |
|
hiyouga
|
91b7fd1ec3
|
fix reserved label len
Former-commit-id: db0ab4d601
|
2024-02-04 17:54:26 +08:00 |
|
hiyouga
|
f6b2bcfa16
|
fix #2420
Former-commit-id: 19d33ede13
|
2024-02-04 15:51:47 +08:00 |
|
hiyouga
|
7cc0721028
|
fix #2189
Former-commit-id: b988ce0a0c
|
2024-02-04 00:47:37 +08:00 |
|
hiyouga
|
b1064d2f9b
|
bump up transformers version
Former-commit-id: 38e63bfd28
|
2024-02-04 00:01:16 +08:00 |
|
hiyouga
|
961368a8c4
|
fix #2397
Former-commit-id: 51df865734
|
2024-02-03 23:45:31 +08:00 |
|
hiyouga
|
0fc8612b97
|
add hint for freeze #2412
Former-commit-id: 6545c02790
|
2024-02-03 23:38:56 +08:00 |
|
hiyouga
|
a9e58740f5
|
fix #2376
Former-commit-id: 4ecadc3512
|
2024-02-03 23:14:31 +08:00 |
|
hiyouga
|
40514bf865
|
support minicpm #2404
Former-commit-id: 901faa16cc
|
2024-02-03 22:36:46 +08:00 |
|
Johann-Peter Hartmann
|
6998b57726
|
add simple german chatml template chatml_de
Former-commit-id: b0ffde6e98
|
2024-02-03 09:01:15 +01:00 |
|
Johann-Peter Hartmann
|
77746ad86c
|
remove comma
Former-commit-id: 870182c3a9
|
2024-02-03 08:48:39 +01:00 |
|
Johann-Peter Hartmann
|
21871df1ad
|
Merge branch 'hiyouga:main' into main
Former-commit-id: 5318cc650e
|
2024-02-03 08:43:12 +01:00 |
|
hoshi-hiyouga
|
fcf1a49e4d
|
Merge pull request #2411 from lxsyz/main
fix eos_token_id=0 bug
Former-commit-id: 2eaaa9522f
|
2024-02-02 17:38:16 +08:00 |
|
Fallen Angel
|
b4c776fa93
|
fix eos_token_id=0 bug
when eos_token_id=0, will never add eos_token
Former-commit-id: 3399c0d645
|
2024-02-02 17:34:48 +08:00 |
|
Johann-Peter Hartmann
|
435db39ab5
|
Merge branch 'hiyouga:main' into main
Former-commit-id: a5d559a89e
|
2024-02-01 07:13:31 +01:00 |
|
hiyouga
|
c3dd4924cc
|
Update wechat.jpg
Former-commit-id: ec70eb5d8d
|
2024-02-01 11:01:12 +08:00 |
|
Johann-Peter Hartmann
|
81edbd1472
|
Merge branch 'hiyouga:main' into main
Former-commit-id: 4e27950acb
|
2024-01-31 14:05:52 +01:00 |
|
hiyouga
|
93a5c22f92
|
fix #2388
Former-commit-id: 39bd5bd524
|
2024-01-31 17:23:56 +08:00 |
|
hiyouga
|
7beeae2209
|
fix autoset attn impl, update data readme
Former-commit-id: 521ad76552
|
2024-01-31 11:58:07 +08:00 |
|
Johann-Peter Hartmann
|
c264eb4793
|
Add support for german datasets
Former-commit-id: d9a8301ed4
|
2024-01-30 10:18:01 +01:00 |
|
hiyouga
|
1aeca5abdf
|
Update wechat.jpg
Former-commit-id: 60733275f8
|
2024-01-25 13:02:49 +08:00 |
|
hiyouga
|
b8a827faeb
|
fix #2320
Former-commit-id: 2bc30763e9
|
2024-01-24 16:19:18 +08:00 |
|
hoshi-hiyouga
|
5928e2ed7c
|
Merge pull request #2319 from ftgreat/main
Add patch_mixtral_replace_moe_impl for full training Mitral using DeepSpeed Zero3
Former-commit-id: 51ad35b3c7
|
2024-01-24 15:32:26 +08:00 |
|
ldwang
|
323ec3f89f
|
Add patch_mixtral_replace_moe_impl for full training Mitral using DeepSpeed Zero3.
Signed-off-by: ldwang <ftgreat@gmail.com>
Former-commit-id: c284665425
|
2024-01-24 15:25:31 +08:00 |
|
ldwang
|
db500a2bb6
|
Add patch_mixtral_replace_moe_impl for full training Mitral using DeepSpeed Zero3.
Signed-off-by: ldwang <ftgreat@gmail.com>
Former-commit-id: 18923b1402
|
2024-01-24 14:43:16 +08:00 |
|
hiyouga
|
cd4d38e0cc
|
Update dataset_info.json
Former-commit-id: dbaaa4546e
|
2024-01-23 00:10:32 +08:00 |
|
hiyouga
|
60a042cc16
|
add hint
Former-commit-id: e4ba1deedf
|
2024-01-22 23:32:01 +08:00 |
|
hoshi-hiyouga
|
8196e9f806
|
Merge pull request #2283 from A-Cepheus/main
fix: ZeRO3 does not work with MoE models
Former-commit-id: 8e4b3a959a
|
2024-01-22 23:28:45 +08:00 |
|
hoshi-hiyouga
|
68977c8ca4
|
Update patcher.py
Former-commit-id: bdc9eff635
|
2024-01-22 23:27:39 +08:00 |
|
hoshi-hiyouga
|
369ac2ca2e
|
Update tests.yml
Former-commit-id: bb5a3b85a6
|
2024-01-22 23:22:15 +08:00 |
|
hoshi-hiyouga
|
e34484051f
|
Create tests.yml
Former-commit-id: 087476da99
|
2024-01-22 23:13:04 +08:00 |
|