SamgeShao
1f1fd98ce6
Update .gitignore
...
Former-commit-id: b2ec86ef63683665382c2fda142c3d9743e3c8a7
2023-12-01 16:37:41 +08:00
hiyouga
eec19b9693
tiny fix
...
Former-commit-id: 37aa7099dff2a9a7b52e259dac92de41ce606946
2023-12-01 15:58:50 +08:00
hoshi-hiyouga
264103aceb
Merge pull request #1695 from Samge0/dev
...
Improve:"CUDA_VISIBLE_DEVICES" read from the env
Former-commit-id: b49cde0c29774820dcf4463e3f1ef00114af7219
2023-12-01 15:56:18 +08:00
hoshi-hiyouga
48db7fd3e9
Merge pull request #1690 from billvsme/main
...
Improve get_current_device
Former-commit-id: c3b8cc27c91248a7381b3333abf099064412dc1a
2023-12-01 15:44:35 +08:00
hiyouga
1602fe2350
fix #1696
...
Former-commit-id: 722ae14a652af34d9b91f9459e613d7959ecaa7e
2023-12-01 15:34:50 +08:00
hoshi-hiyouga
634da9ee68
Merge pull request #1689 from mlinmg/patch-2
...
Update dataset_info.json - Added Nectar
Former-commit-id: 50b029fa981576e4be1a7a08b62f9e0109c085e0
2023-12-01 14:29:36 +08:00
samge
eda1acb191
Improve:"CUDA_VISIBLE_DEVICES" read from the env
...
Former-commit-id: 7a61daa8be76779c876d685c57c464133ca70752
2023-12-01 11:35:02 +08:00
Marco
238379e64a
Update dataset_info.json
...
Added the Nectar dataset already preprocessed and divided in sft and rl to which I added a preprompt to each instruction since it has been seen that this increase instruction following
Former-commit-id: 6336e247c1535f356194046607038245bc48464f
2023-11-30 16:21:34 +01:00
billvsme
bd907d8dce
improve get_current_device
...
Former-commit-id: 2b07815e7fc8dc6ad0a7e9eccdd6681fbab35f3c
2023-11-30 22:40:35 +08:00
hiyouga
24dd0db807
fix #1597
...
Former-commit-id: d77a3a79a0e854803a57af8ac6a7246691f69f70
2023-11-30 21:47:06 +08:00
hiyouga
ca70d8393d
fix #1668
...
Former-commit-id: bccc71259e703ca1e1d88169e385a026c4efa92e
2023-11-30 21:02:00 +08:00
hiyouga
4f3699efd2
fix #1682
...
Former-commit-id: 06d56696731eadbeeea615eae4efce1b6c36def4
2023-11-30 20:03:32 +08:00
hiyouga
46066ed801
add models
...
Former-commit-id: b9eaadde8b5f4b9f89fa7bb910b325fcf9c84434
2023-11-30 19:16:13 +08:00
hiyouga
9e509b7613
add gpu requirement #1657
...
Former-commit-id: 8581a9133790573031d9615a551fb677eb3be461
2023-11-29 12:05:03 +08:00
hiyouga
d072f771d2
fix #1658
...
Former-commit-id: 3126687c4820c34daa6a2e9e3bf9065ad59e92dc
2023-11-28 20:57:24 +08:00
hiyouga
a073c3824a
fix #1659
...
Former-commit-id: e4123129aae59f4123d53c1f5320e3d5e09ae26d
2023-11-28 20:52:28 +08:00
hiyouga
7796b04ddb
support export size setting
...
Former-commit-id: 1a4de54586c21cdbbc89f8a716ca5a54c87a6120
2023-11-26 18:34:09 +08:00
hiyouga
0b9b68b10b
support Yi-34B-Chat models
...
Former-commit-id: 1751a79c27e7fc13e76a731a061dc0c10d828cda
2023-11-23 19:31:49 +08:00
hiyouga
36fbe36b10
update readme
...
Former-commit-id: 561481a8008fde5a3273558460193864a09866ed
2023-11-21 13:15:46 +08:00
hiyouga
0aceb31b04
set version
...
Former-commit-id: 6b47ad74c7b3099f9b5087c73db4aee42c451297
2023-11-20 22:57:44 +08:00
hiyouga
da30d9ba02
support GPTQ tuning #729 #1481 #1545 , fix chatglm template #1453 #1480 #1569
...
Former-commit-id: fdccc6cc9b68890199e9250cabdb996ff2f853b9
2023-11-20 22:52:11 +08:00
hiyouga
78e6ac0156
update ppo trainer
...
Former-commit-id: caa525a5c6f228b9ad71387d1fe4f1c2ffa2479e
2023-11-20 21:39:15 +08:00
hoshi-hiyouga
05fd97c637
Merge pull request #1553 from hannlp/hans
...
Change the default argument settings for PPO training
Former-commit-id: 1b64678fa4979485f67c3bb1420dfdff6fcbc6e7
2023-11-20 20:32:55 +08:00
hiyouga
c815b51fef
fix value head model resuming
...
Former-commit-id: ccf0b65d886c09c7c49977c43b0544fe1bfcc258
2023-11-20 19:01:37 +08:00
hiyouga
4febd99b99
fix #1567
...
Former-commit-id: 8c01ffe8d277d49a413571e0669f460c8d0802bf
2023-11-20 18:46:36 +08:00
hiyouga
8e50cc3c5b
better data streaming
...
Former-commit-id: 65ac8e84fd6f22255c587b20382fdf5d8131d015
2023-11-19 23:32:47 +08:00
hiyouga
6f64aeeba2
fix model card network issue
...
Former-commit-id: 36155cd1893bea036f15c648c06b0047c02dfb4f
2023-11-19 23:03:19 +08:00
hiyouga
1809e1c7a0
fix Mistral template
...
https://github.com/lm-sys/FastChat/pull/2547
Former-commit-id: d426ecdf6e95402fc36893f7e4f17f881e1b957b
2023-11-19 16:29:30 +08:00
hiyouga
2dba8ad987
fix #1263
...
Former-commit-id: faff5d32621f187ebd3124d7ade04e3fa437c53e
2023-11-19 16:05:18 +08:00
hiyouga
226156bdf1
fix #1558
...
Former-commit-id: 263b2b24c8a649b51fa5ae768a24e67def8e0e96
2023-11-19 14:15:47 +08:00
hiyouga
d4a5f2e2e6
fix evaluator and cached_file in 4.31.0
...
Former-commit-id: 970897da402f604220d45084d492de4dab809ba4
2023-11-18 19:39:23 +08:00
hiyouga
47d921f9f0
update benchmark
...
Former-commit-id: 1cd2ae910e3ffca92978772d000de6fde2f6bb13
2023-11-18 11:30:01 +08:00
hiyouga
633a1da456
update readme
...
Former-commit-id: a4d86a4bea1cce2219a54def9dfd3fd732d48e72
2023-11-18 11:15:56 +08:00
hiyouga
2f593a7d66
add benchmark
...
Former-commit-id: 85a09cb649be740a47359371499d821ee0d5c81e
2023-11-18 11:09:52 +08:00
hiyouga
c7ab341fcd
update dataset
...
Former-commit-id: a310b22b446118d90dd73906847ed3d01a574b50
2023-11-17 23:19:12 +08:00
hiyouga
04ec7df2f3
fix quantization
...
Former-commit-id: 8268aefe8fba268065e24ffe159a9c49f7c6f3a5
2023-11-17 22:21:29 +08:00
hiyouga
1cb75c81d7
fix #1550
...
Former-commit-id: c12acd21a5a500892ed739c79327ccd39fddad5b
2023-11-17 17:23:13 +08:00
Yuchen Han
3f7cdf71ad
Update README_zh.md
...
Former-commit-id: 3e8a17c92d700bcafbe6559ea689dc4c0ad0481a
2023-11-17 00:18:07 -08:00
Yuchen Han
d455ca2391
Update README.md
...
Former-commit-id: c1532dc6fe5d5b427011bd5509a2bc44ee16d951
2023-11-17 00:17:36 -08:00
Yuchen Han
b6c80a4d43
Update workflow.py
...
Former-commit-id: f70b7ffe6442217a222e0ef797c407f259a13886
2023-11-17 00:16:27 -08:00
Yuchen Han
632158ce8e
Update finetuning_args.py
...
Former-commit-id: 30e3430553f1f7e09cd57ef2c9843b549746c618
2023-11-17 00:15:51 -08:00
hiyouga
300b2f7ff4
fix packages
...
Former-commit-id: c93175d18ad9a4b7b61629153acabf8d0c978dfc
2023-11-17 16:11:48 +08:00
hoshi-hiyouga
4c1e9305b6
Merge #1544 from Outsider565/main, fix #1548
...
Fix: Change rouge-chinese package name to rouge_chinese
Former-commit-id: c24da51cb5d3f78d54dcbfb31b565fcac4783a76
2023-11-17 16:09:42 +08:00
Shaowen Wang
5938ac23df
Fix: Change rouge-chinese package name to rouge_chinese
...
To reproduce:
python:
importlib.util.find_spec('rouge-chinese') -> None
importlib.util.find_spec('rouge_chinese') -> ModuleSpec(name='rouge_chinese'...)
from rouge_chinese import Rouge
print(Rouge.__module__) -> rouge_chinese
Former-commit-id: a78b11d944b6cb7dbe2a1d8a24d240e196aa530a
2023-11-16 20:12:35 -06:00
hiyouga
18f3c59400
fix chatglm template
...
Former-commit-id: 6a4b79c2e0610a17012bf3e72a2b5e8bac060092
2023-11-16 22:54:15 +08:00
hiyouga
c10cf4a358
Update bug-report.yml
...
Former-commit-id: 92ed2297c78d016113fa7f90cedc0933a0bb2be0
2023-11-16 19:37:35 +08:00
hiyouga
444d111244
add issue template
...
Former-commit-id: 4ca01a6b051043593541403d74e4d464b70e0e4b
2023-11-16 19:35:30 +08:00
hoshi-hiyouga
3ce0fa0f39
Update issue templates
...
Former-commit-id: f967abcfcd052b65745f20e2c760ca45c412b66a
2023-11-16 18:56:30 +08:00
hiyouga
5a1409679f
fix web ui demo
...
Former-commit-id: e566a68a27872f730b111078977048755ec74a40
2023-11-16 18:41:55 +08:00
hiyouga
22322a3fa1
fix web ui demo
...
Former-commit-id: 6fead193fe44fec74c2262d8653ed2f6006fac36
2023-11-16 17:12:23 +08:00