hiyouga
|
384f0e7678
|
add bf16 lora option
Former-commit-id: 58e7d7ff0cf9bf30e53b3eb12576f38d31976413
|
2024-01-19 16:29:03 +08:00 |
|
hiyouga
|
d1ec884e75
|
fix #2195
Former-commit-id: 801f7279693a0c785480ea67d663d99f4ca653da
|
2024-01-16 23:53:50 +08:00 |
|
hiyouga
|
921f593632
|
update loader
Former-commit-id: 080d8eab858217ca58bffe719d5ffde7579c5bda
|
2023-12-24 19:10:23 +08:00 |
|
hiyouga
|
6faf9c35a9
|
support unsloth
Former-commit-id: b857f00234b90b785d82ca7cdb29af3d948b1a7b
|
2023-12-23 00:14:33 +08:00 |
|
hiyouga
|
67f7034a21
|
fix param type
Former-commit-id: 11b99f344416ade1cdac52e11ba7f36fcf689221
|
2023-12-21 17:33:01 +08:00 |
|
hiyouga
|
d81ad2d4bc
|
support dpo-ftx
Former-commit-id: 86dfa04f9821556019fa777106787f73eb70b452
|
2023-12-16 19:21:41 +08:00 |
|
hiyouga
|
296711d502
|
support quantization in export model
Former-commit-id: f32500ae6edccab7d14df4c92467e15986866def
|
2023-12-15 23:44:50 +08:00 |
|
hiyouga
|
f902b0d420
|
refactor adapter hparam
Former-commit-id: f82aece9ebd6df83a7a005cc7cbbcec07fa6e14d
|
2023-12-15 20:53:11 +08:00 |
|
hiyouga
|
2542b62d77
|
remove loftq
Former-commit-id: e175c0a1c631296117abda2403a4b87bbdd35a66
|
2023-12-13 01:53:46 +08:00 |
|
hiyouga
|
e39bbdd287
|
support loftq
Former-commit-id: e7ac2eb7f7daae17525a278ffbe2f82c0fbd8093
|
2023-12-12 22:47:06 +08:00 |
|
hiyouga
|
9e2cc21d04
|
update readme
Former-commit-id: 42e042a4206aeb5177ddde56386e9655b0c06460
|
2023-12-12 11:44:30 +08:00 |
|
hiyouga
|
29545d0e5e
|
implement rm server #1543
Former-commit-id: 2e5bb6888c86079493456c2ddd525f8c52b9963e
|
2023-12-03 20:52:54 +08:00 |
|
hiyouga
|
670ee3934f
|
fix #1659
Former-commit-id: e4123129aae59f4123d53c1f5320e3d5e09ae26d
|
2023-11-28 20:52:28 +08:00 |
|
hiyouga
|
569860d7ac
|
support export size setting
Former-commit-id: 1a4de54586c21cdbbc89f8a716ca5a54c87a6120
|
2023-11-26 18:34:09 +08:00 |
|
hiyouga
|
28258aecd2
|
update ppo trainer
Former-commit-id: caa525a5c6f228b9ad71387d1fe4f1c2ffa2479e
|
2023-11-20 21:39:15 +08:00 |
|
Yuchen Han
|
bcd31cf245
|
Update finetuning_args.py
Former-commit-id: 30e3430553f1f7e09cd57ef2c9843b549746c618
|
2023-11-17 00:15:51 -08:00 |
|
hiyouga
|
de3a84ac59
|
fix rlhf callback
Former-commit-id: f5485452d660caef56474cb7dc37abbe4f34599e
|
2023-11-16 03:26:19 +08:00 |
|
hiyouga
|
e017266b98
|
fix bug in PPO training
Former-commit-id: 2e99f0e53ce6de0acbcab85dd50aef874e8c6336
|
2023-11-16 02:32:54 +08:00 |
|
hiyouga
|
7a3a0144a5
|
support full-parameter PPO
Former-commit-id: 4af967d69475e1c9fdf1a7983cd6b83bd431abff
|
2023-11-16 02:08:04 +08:00 |
|
hiyouga
|
b2ac8376e1
|
support multiple modules in freeze training #1514
Former-commit-id: 60abac70dfd778df2ae8b3a2e960ed8b607d7ab6
|
2023-11-15 17:08:18 +08:00 |
|
hiyouga
|
64fc9ba678
|
refactor evaluation, upgrade trl to 074
Former-commit-id: ed09ebe2c1926ffdb0520b3866f7fd03a9aed046
|
2023-11-13 22:20:35 +08:00 |
|
hiyouga
|
68dd1ef121
|
tiny fix
Former-commit-id: 97ba2027bb1ddc01a3c824c40d5a180828810c2c
|
2023-11-09 17:20:49 +08:00 |
|
Yanqing
|
b4f1ab93d1
|
Update finetuning_args.py
更新 chatglm/falcon/bloom 的 lora_target 的名称
Former-commit-id: 06606739af035a80ae9ddba9d12c965ed289305d
|
2023-11-09 17:04:40 +08:00 |
|
hiyouga
|
f5ba2190fb
|
fix ppo train and dpo eval
Former-commit-id: ced863031836632cb5920e22ae6991f251372118
|
2023-11-07 22:48:51 +08:00 |
|
hiyouga
|
2eb65d21ac
|
upgrade peft, fix #1088 #1411
Former-commit-id: aa7d104f8e050d12cb8f585bc8a52c850995500f
|
2023-11-07 16:13:36 +08:00 |
|
hiyouga
|
6da51565f5
|
reimplement neftune
Former-commit-id: efe9e5a194d3a9f052701d904715238816e4c09e
|
2023-10-22 16:15:08 +08:00 |
|
anvie
|
af2d61178d
|
add NEFTune optimization
Former-commit-id: 603e0298af64116ac07130fe6661a9ba823c186c
|
2023-10-21 13:24:10 +07:00 |
|
hiyouga
|
c2e84d4558
|
refactor export, fix #1190
Former-commit-id: 30e60e37023a7c4a2db033ffec0542efa3d5cdfb
|
2023-10-15 16:01:48 +08:00 |
|
hiyouga
|
97b74d328b
|
fix ppo args
Former-commit-id: 0f12899951808f53a482082eb116bda309775930
|
2023-10-11 23:40:50 +08:00 |
|
hiyouga
|
386d85ae72
|
refactor finetuning Args
Former-commit-id: be425a70a4c8f051717cf1e4464dbd79dae4c0b5
|
2023-09-27 22:28:06 +08:00 |
|
hiyouga
|
6310613699
|
update template
Former-commit-id: a95f3a4d62de1073a78125401cf4289ec0523156
|
2023-08-22 19:46:09 +08:00 |
|
hiyouga
|
2b191ca776
|
support ppo score norm (trl 0.5.1.dev required)
Former-commit-id: 2b25db6d260ec1532281a592e873579346c7d21c
|
2023-08-18 12:02:42 +08:00 |
|
hiyouga
|
be4d2822ea
|
fix PPO trainer #551 , update readme
Former-commit-id: faead74849470cebae9e37cde5fab2a71b32aa43
|
2023-08-18 11:43:10 +08:00 |
|
hiyouga
|
d5f1b99ac4
|
Release v0.1.6
Former-commit-id: 43c8b3c3c8bfb2e32d17fb3e8b194938e37d54bd
|
2023-08-11 23:25:57 +08:00 |
|
hiyouga
|
ca719a8697
|
support DPO training (2305.18290)
Former-commit-id: 6d98de148e4af63a7028dfaeb6cf86eb56a4488f
|
2023-08-11 03:02:53 +08:00 |
|
hiyouga
|
15acd17716
|
update args spec
Former-commit-id: a006068346edda6e2851b23d2005fdb218a7287d
|
2023-08-07 15:23:35 +08:00 |
|
hiyouga
|
2e19afedb8
|
support Qwen-7B, fix InternLM-7B inference
Former-commit-id: 25d2ca29ecb70cbfd5206333c667042a0c4d2e5a
|
2023-08-03 15:53:32 +08:00 |
|
hiyouga
|
bcdee9fc19
|
fix #194
Former-commit-id: 9792921531efefb4bcddbde4380169a78fe064a6
|
2023-07-19 17:07:33 +08:00 |
|
hiyouga
|
a8deee27f8
|
create chat model
Former-commit-id: bddf583b2fc099c957a1037418bd8504a837663e
|
2023-07-15 19:26:20 +08:00 |
|
hiyouga
|
6261fb362a
|
modity code structure
Former-commit-id: 0682ed357210897e0b67c4a6eb31a94b3eb929f1
|
2023-07-15 16:54:28 +08:00 |
|