marko1616
645c27e5e2
fix Llama lora merge crash
...
Former-commit-id: 51349ea1cc
2024-03-24 02:55:23 +08:00
marko1616
c083708433
fix Llama lora merge crash
...
Former-commit-id: c1e2c4ea45
2024-03-24 02:44:35 +08:00
hiyouga
84c3d509fa
fix #2936
...
Former-commit-id: 140ad4ad56
2024-03-24 00:43:21 +08:00
hiyouga
75829c8699
fix #2928
...
Former-commit-id: 7afbc85dae
2024-03-24 00:34:54 +08:00
hiyouga
58aa576ae5
fix #2941
...
Former-commit-id: a1c8c98c5f
2024-03-24 00:28:44 +08:00
hiyouga
c765b4c1ac
Update wechat.jpg
...
Former-commit-id: 564d57aa23
2024-03-22 14:00:37 +08:00
hoshi-hiyouga
4e067329a3
Merge pull request #2919 from 0xez/main
...
Update README.md, fix the release date of the paper
Former-commit-id: ce261fdd64
2024-03-22 12:12:24 +08:00
0xez
028a8bc532
Update README_zh.md, fix the release date of the paper
...
Former-commit-id: be0360303d
2024-03-22 10:41:17 +08:00
0xez
3f50d572ed
Update README.md, fix the release date of the paper
...
Former-commit-id: 675ba41562
2024-03-21 22:14:48 +08:00
hiyouga
cfcea16416
move file
...
Former-commit-id: 96702620c4
2024-03-21 17:05:17 +08:00
hiyouga
63c83f3802
add citation
...
Former-commit-id: 5eaa50fa01
2024-03-21 17:04:10 +08:00
hiyouga
0684e315be
paper release
...
Former-commit-id: 0581bfdbc7
2024-03-21 13:49:17 +08:00
hiyouga
ada7e20eb4
update readme
...
Former-commit-id: bfe7a91289
2024-03-21 00:48:42 +08:00
hiyouga
7999836fb6
support fsdp + qlora
...
Former-commit-id: 8408225162
2024-03-21 00:36:06 +08:00
hiyouga
6646e18c02
add orca_dpo_pairs dataset
...
Former-commit-id: 3271af2afc
2024-03-20 20:09:06 +08:00
hoshi-hiyouga
e8cf2794cd
Merge pull request #2905 from SirlyDreamer/main
...
Follow HF_ENDPOINT environment variable
Former-commit-id: b2dfbd728f
2024-03-20 18:09:54 +08:00
hiyouga
8717e98200
fix #2777 #2895
...
Former-commit-id: 9bec3c98a2
2024-03-20 17:59:45 +08:00
hiyouga
cf149bf43c
fix #2346
...
Former-commit-id: 7b8f502901
2024-03-20 17:56:33 +08:00
SirlyDreamer
78359638e3
Follow HF_ENDPOINT environment variable
...
Former-commit-id: e165965341
2024-03-20 08:31:30 +00:00
hoshi-hiyouga
a9d85cf3c6
Merge pull request #2903 from khazic/main
...
Updated README with new information
Former-commit-id: a773035709
2024-03-20 16:13:44 +08:00
khazic
c7824c42ff
Updated README with new information
...
Former-commit-id: 8d10fa71c2
2024-03-20 14:38:08 +08:00
khazic
13bf8b1f91
Updated README with new information
...
Former-commit-id: 0531dac30d
2024-03-20 14:21:16 +08:00
刘一博
5b8725399e
Updated README with new information
...
Former-commit-id: df9b4fb90a
2024-03-20 14:11:28 +08:00
hiyouga
7fbdbc2419
Update wechat.jpg
...
Former-commit-id: bea31b9b12
2024-03-18 16:48:32 +08:00
hiyouga
3d483e0914
fix packages
...
Former-commit-id: 8e04794b2d
2024-03-17 22:32:03 +08:00
hiyouga
a5537f3ee8
fix patcher
...
Former-commit-id: 85c376fc1e
2024-03-15 19:18:42 +08:00
hoshi-hiyouga
30765baa91
Merge pull request #2849 from S3Studio/DockerizeSupport
...
Improve Dockerize support
Former-commit-id: 113cc04719
2024-03-15 19:16:02 +08:00
hiyouga
06860e8f0f
fix export
...
Former-commit-id: 6bc2c23b6d
2024-03-15 15:06:30 +08:00
S3Studio
46ef7416e6
Use official Nvidia base image
...
Note that the flash-attn library is installed in this image and the qwen model will use it automatically.
However, if the the host machine's GPU is not compatible with the library, an exception will be raised during the training process as follows:
FlashAttention only supports Ampere GPUs or newer.
So if the --flash_attn flag is not set, an additional patch for the qwen model's config is necessary to set the default value of use_flash_attn from "auto" to False.
Former-commit-id: e75407febd
2024-03-15 08:59:13 +08:00
S3Studio
dcbc8168a8
improve Docker build and runtime parameters
...
Modify installation method of extra python library.
Utilize shared memory of the host machine to increase training performance.
Former-commit-id: 6a5693d11d
2024-03-15 08:57:46 +08:00
hiyouga
7ef49586be
tiny fix
...
Former-commit-id: 6ebde4f23e
2024-03-14 21:19:06 +08:00
hiyouga
2cf95d4efe
fix export
...
Former-commit-id: 3b4a59bfb1
2024-03-14 18:17:01 +08:00
hiyouga
edd28dbe2c
fix bug
...
Former-commit-id: 8172530d54
2024-03-13 23:55:31 +08:00
hiyouga
9ff7c99eb1
fix bug
...
Former-commit-id: 714d936dfb
2024-03-13 23:43:42 +08:00
hiyouga
8b8671817f
improve lora+ impl.
...
Former-commit-id: 72367307df
2024-03-13 23:32:51 +08:00
hoshi-hiyouga
4000de93ea
Merge pull request #2830 from qibaoyuan/lora_plus
...
[FEATURE]: ADD LORA+ ALGORITHM
Former-commit-id: 4e5e99af43
2024-03-13 20:15:46 +08:00
齐保元
24c9277488
[FEATURE]: ADD LORA+ ALGORITHM
...
Former-commit-id: a0965cd62c
2024-03-13 19:43:27 +08:00
hiyouga
634c44c51a
Update wechat.jpg
...
Former-commit-id: dfd451b722
2024-03-13 19:03:00 +08:00
hiyouga
922bd8864b
fix #2817
...
Former-commit-id: 0b4a5bf509
2024-03-13 12:42:03 +08:00
hiyouga
8673abbe5e
fix #2802
...
Former-commit-id: b9f87cdc11
2024-03-13 12:33:45 +08:00
hiyouga
a74426df0f
fix kv cache
...
Former-commit-id: 96ce76cd27
2024-03-13 01:21:50 +08:00
hiyouga
bbf272f96e
support QDoRA
...
Former-commit-id: 19ef482649
2024-03-12 22:12:42 +08:00
hiyouga
096c31bfb6
patch for gemma cpt
...
Former-commit-id: 70a3052dd8
2024-03-12 21:21:54 +08:00
hiyouga
c28818c39f
fix plot issues
...
Former-commit-id: 60cc17f3a8
2024-03-12 18:41:35 +08:00
hiyouga
14ed926a2d
support olmo
...
Former-commit-id: b3247d6a16
2024-03-12 18:30:38 +08:00
hiyouga
0b7e870b07
fix #2802
...
Former-commit-id: 8d8956bad5
2024-03-12 17:08:34 +08:00
hiyouga
b983de9f4f
fix #2803
...
Former-commit-id: 06c97083e1
2024-03-12 16:57:39 +08:00
hiyouga
7124b71676
fix #2782 #2798
...
Former-commit-id: 07f9b754a7
2024-03-12 15:53:29 +08:00
hoshi-hiyouga
52f14211e3
Merge pull request #2743 from S3Studio/DockerizeSupport
...
Add dockerize support
Former-commit-id: c901aa63ff
2024-03-12 00:05:49 +08:00
hiyouga
c88062347e
fix #2775
...
Former-commit-id: e874c00906
2024-03-11 00:42:54 +08:00
