hiyouga
|
3382317e32
|
refactor mm training
|
2024-08-30 02:14:31 +08:00 |
|
hiyouga
|
ad72f3e065
|
fix #5295
|
2024-08-29 20:30:18 +08:00 |
|
hiyouga
|
b7ca6c8dc1
|
fix #5048
|
2024-08-05 23:48:19 +08:00 |
MengqingCao
|
7d4a293033
|
update dependencies
|
2024-06-20 02:09:47 +00:00 |
hoshi-hiyouga
|
e8c518c08a
|
Update requirements.txt
|
2024-06-18 22:27:24 +08:00 |
胡翀
|
12869c3ede
|
Update requirements.txt
add pandas version requirements
|
2024-06-17 16:45:57 +08:00 |
|
hiyouga
|
f9e818d79c
|
fix #4120
|
2024-06-07 04:18:05 +08:00 |
|
hiyouga
|
67fe822324
|
fix #4090
|
2024-06-06 00:50:32 +08:00 |
|
hiyouga
|
83a005e3d4
|
fix #4079
|
2024-06-05 16:56:54 +08:00 |
|
hiyouga
|
876bc92865
|
bump versions
transformers 4.37.2->4.41.2
datasets 2.14.3->2.16.0
accelerate 0.27.2->0.30.1
peft 0.10.0->0.11.1
trl 0.8.1->0.8.6
|
2024-06-03 18:29:38 +08:00 |
|
hiyouga
|
75aec4cf8e
|
resolve python 3.8 package
|
2024-05-09 16:52:27 +08:00 |
|
hiyouga
|
10ab83f4c4
|
add deepseek moe 236B
|
2024-05-08 16:37:54 +08:00 |
|
hiyouga
|
245fe47ece
|
update webui and add CLIs
|
2024-05-03 02:58:23 +08:00 |
|
hiyouga
|
07737a3d2d
|
reenable sdpa and fast tok by default
|
2024-04-24 02:18:44 +08:00 |
|
hiyouga
|
5d62a51c12
|
update readme and gradio version
|
2024-04-16 18:09:16 +08:00 |
|
hiyouga
|
4b920f24d3
|
back to gradio 4.21 and fix chat
|
2024-04-04 02:07:20 +08:00 |
|
hiyouga
|
5ddcecda50
|
fix bug in latest gradio
|
2024-04-04 00:55:31 +08:00 |
|
hiyouga
|
7f6e412604
|
fix requires for windows
|
2024-04-03 21:56:43 +08:00 |
|
hiyouga
|
831c5321ac
|
upgrade gradio to 4.21.0
|
2024-03-30 20:37:08 +08:00 |
|
hiyouga
|
1e43319f9c
|
add project
|
2024-03-28 20:24:27 +08:00 |
Remek Kinas
|
b02899bf89
|
Update requirements.txt
|
2024-03-25 14:30:58 +01:00 |
|
hiyouga
|
8408225162
|
support fsdp + qlora
|
2024-03-21 00:36:06 +08:00 |
|
hiyouga
|
06c97083e1
|
fix #2803
|
2024-03-12 16:57:39 +08:00 |
|
hiyouga
|
28f7862188
|
support galore
|
2024-03-07 22:41:36 +08:00 |
|
hiyouga
|
cfefacaa37
|
support DoRA, AWQ, AQLM #2512
|
2024-02-28 19:53:28 +08:00 |
Katehuuh
|
7dc352a4c2
|
bump accelerate
|
2024-02-27 08:56:45 +01:00 |
|
hiyouga
|
7924ffc55d
|
support llama pro #2338 , add rslora
|
2024-02-15 02:27:36 +08:00 |
|
hiyouga
|
38e63bfd28
|
bump up transformers version
|
2024-02-04 00:01:16 +08:00 |
|
hiyouga
|
d9f1cae351
|
support function calling
|
2024-01-18 09:54:23 +08:00 |
|
hiyouga
|
3ae735ffe8
|
fix #2125
|
2024-01-08 21:42:25 +08:00 |
Dristanta Das
|
e4cde81851
|
Update requirements.txt With einops dependency
|
2024-01-07 21:03:30 +05:30 |
|
hiyouga
|
7aad0b889d
|
support unsloth
|
2023-12-23 00:14:33 +08:00 |
ShaneTian
|
390f0caf7f
|
Update transformers to 4.36.2 to resolve bug when saving a checkpoint in the multi-node setting.
|
2023-12-20 22:00:41 +08:00 |
|
hiyouga
|
b87c74289d
|
support dpo-ftx
|
2023-12-16 19:21:41 +08:00 |
|
hiyouga
|
0716f5e470
|
refactor adapter hparam
|
2023-12-15 20:53:11 +08:00 |
|
hoshi-hiyouga
|
9b0630f84f
|
revert peft version
|
2023-12-13 10:49:45 +08:00 |
|
hoshi-hiyouga
|
573a12c86b
|
update peft version
|
2023-12-13 10:23:51 +08:00 |
|
hiyouga
|
96380f5e18
|
support mixtral
|
2023-12-12 11:39:04 +08:00 |
|
hiyouga
|
9ce1b0e2f2
|
use peft 0.7.0, fix #1561 #1764
|
2023-12-11 17:13:40 +08:00 |
|
hiyouga
|
d42c0b1d34
|
fix #1771 and temporarily fix #1764
|
2023-12-08 16:26:20 +08:00 |
|
hiyouga
|
442aefb925
|
refactor evaluation, upgrade trl to 074
|
2023-11-13 22:20:35 +08:00 |
|
hiyouga
|
33422e1fef
|
fix #1438 #1439
|
2023-11-09 13:45:10 +08:00 |
|
hiyouga
|
7ebd63a609
|
fix #1418
|
2023-11-07 16:17:22 +08:00 |
|
hiyouga
|
b2a60905f3
|
upgrade peft, fix #1088 #1411
|
2023-11-07 16:13:36 +08:00 |
|
hiyouga
|
66a91e1fe3
|
update requirements
|
2023-11-06 19:01:21 +08:00 |
|
hiyouga
|
84af10cec9
|
update gradio, support multiple resp in api
|
2023-11-01 23:02:16 +08:00 |
|
hiyouga
|
838ed9aa87
|
fix #1287
|
2023-10-26 17:49:41 +08:00 |
|
hiyouga
|
a6a04be2e6
|
fix config, #1191
|
2023-10-15 18:28:45 +08:00 |
|
hiyouga
|
8e2ed6b8ce
|
update readme
|
2023-10-09 20:02:50 +08:00 |
|
hiyouga
|
b8dbec086e
|
update webui #1086
|
2023-10-09 14:50:14 +08:00 |