hiyouga
|
1fe1ca1c8b
|
add orion models
Former-commit-id: a34db89d2a281d1a1ace29dfd5bd5d4ff7c2f657
|
2024-01-22 21:26:53 +08:00 |
|
A-Cepheus
|
882a6a1d51
|
🐞 fix: typo
Former-commit-id: 57a3687ecd23237559aee0e8e811b782846f2415
|
2024-01-22 16:04:39 +08:00 |
|
A-Cepheus
|
712ab4ae7a
|
🐞 fix: typo, move MoE fix to patcher
Former-commit-id: 4ff28e99ff9b48df7150591c6bbd3723f22b7715
|
2024-01-22 16:01:58 +08:00 |
|
A-Cepheus
|
18ad259fb3
|
fix: ZeRO3 does not work with MoE models
Former-commit-id: b2844c049a88ea89f8e1812e2d2e8662b4002965
|
2024-01-22 15:21:14 +08:00 |
|
hiyouga
|
fe4d93c6db
|
add array param format
Former-commit-id: bf910f8a5b21ee552fa9ab069610a3f5f611de57
|
2024-01-21 22:17:48 +08:00 |
|
hiyouga
|
c6ba588e37
|
update tool test
Former-commit-id: 1d63ccc2866632596310235de15fdff660f6bee5
|
2024-01-21 19:41:46 +08:00 |
|
hiyouga
|
3fda60fca0
|
fix api
Former-commit-id: cca004da28aaaa0788eaea62b83d3402b38a3011
|
2024-01-21 19:15:27 +08:00 |
|
hiyouga
|
96531a0ef8
|
fix #2268
Former-commit-id: 300ecf9b9d7fd99fbb68f3d086e3ad973c2f894e
|
2024-01-21 14:11:38 +08:00 |
|
hiyouga
|
7abc3065fb
|
tiny fix
Former-commit-id: 66839ae94985ddfa13eca4542127119c919b9648
|
2024-01-21 13:26:12 +08:00 |
|
hoshi-hiyouga
|
013ded4bac
|
Merge pull request #2266 from yhyu13/fix_export_model_dtype
Remove manully set use_cache; torch_dtype is not str, save model as b…
Former-commit-id: 8c0827ba92a458e18c3b68af0330af3a65149f96
|
2024-01-21 12:40:39 +08:00 |
|
hoshi-hiyouga
|
010c3c7348
|
Merge branch 'main' into fix_export_model_dtype
Former-commit-id: 6c7d2729f28eb37a97820d73c05648eb7fb2ca87
|
2024-01-21 12:40:24 +08:00 |
|
hoshi-hiyouga
|
bf075c075c
|
Update tuner.py
Former-commit-id: 691420661f7115f809e76484c1f29f74637e7cd0
|
2024-01-21 12:39:38 +08:00 |
|
hoshi-hiyouga
|
41b34e5f60
|
Merge pull request #2262 from fenglui/main
fix torch_dtype check of export_model
Former-commit-id: 37cacf73a534fed1b06b4f3c6724f3568ce095e3
|
2024-01-21 12:34:37 +08:00 |
|
hiyouga
|
5a889398e7
|
format
Former-commit-id: f28a1a0c1cdd0062ad7b6c2826f8ec107a200cff
|
2024-01-21 12:34:17 +08:00 |
|
hoshi-hiyouga
|
054cae86d8
|
Merge pull request #2264 from seoeaa/main
add russian lang
Former-commit-id: 15d1747de54efe69ed9f4cfd8f296fe8dd09a5c9
|
2024-01-21 12:25:24 +08:00 |
|
yhyu13
|
cd1cb8b83c
|
Remove manully set use_cache; torch_dtype is not str, save model as bfloat16 used to fail;
Former-commit-id: 75557fb5df16fd6eda7586cf041a16822dcfee8e
|
2024-01-21 11:12:15 +08:00 |
|
Aleksandr
|
a34779c027
|
add russian lang
Former-commit-id: f8ce6d75b56439027bb17ff4e59eeb9eb3b9bd34
|
2024-01-21 04:28:14 +03:00 |
|
fenglui
|
d19cb77d74
|
fix torch_dtype check of export_model
Former-commit-id: 8813181b6bffa76e5c7cb1f4caceada611c54b9d
|
2024-01-21 05:01:53 +08:00 |
|
hiyouga
|
ab67528e89
|
release v0.5.0 (real)
Former-commit-id: 2146e1d9195c179fa8f92144ec2b7034e1a9f942
v0.5.0
|
2024-01-21 01:54:49 +08:00 |
|
hiyouga
|
27f281480a
|
finish agent
Former-commit-id: d8d9d3afe32725fe79120fcd1a0970fdcdc45625
|
2024-01-21 01:47:33 +08:00 |
|
hiyouga
|
50459a39f4
|
fix api
Former-commit-id: a4149fbcd600d4f3815f9353e5e92c569719bed6
|
2024-01-21 00:03:09 +08:00 |
|
hiyouga
|
5c9815ef6f
|
fix internlm2 template
Former-commit-id: ae05b23eb86555dbfafc174aa6ceff736e7fc9fa
|
2024-01-20 23:33:50 +08:00 |
|
hiyouga
|
aed00a97b6
|
fix cli_demo
Former-commit-id: e8336b3653f43618cf7cd70f8da004208de970c0
|
2024-01-20 23:27:10 +08:00 |
|
hiyouga
|
7543dc4a9d
|
fix #2260
Former-commit-id: ba97550671811a27177306dd231bb427130b26fb
|
2024-01-20 23:22:09 +08:00 |
|
hiyouga
|
841fa0030f
|
release v0.5.0
Former-commit-id: 602bb9b685009b9af234499be278404721542ac7
|
2024-01-20 20:21:39 +08:00 |
|
hiyouga
|
66e0e651b9
|
format style
Former-commit-id: 53b683531b83cd1d19de97c6565f16c1eca6f5e1
|
2024-01-20 20:15:56 +08:00 |
|
hiyouga
|
1750218057
|
fix tests
Former-commit-id: 23f97bd437424ef43b2b84743d56acc5d1ca70d5
|
2024-01-20 19:58:04 +08:00 |
|
hiyouga
|
80637fc06d
|
support longlora for main branch
Former-commit-id: f869501ad4c368df26534c41f62c6d63c6be17dd
|
2024-01-20 19:25:22 +08:00 |
|
hoshi-hiyouga
|
8efc055511
|
Merge pull request #2201 from liu-zichen/token_embed_resize
support resize embed for zero3
Former-commit-id: c0d1b5e3aef70da6b115614bd1ed539a76d6547a
|
2024-01-20 17:45:38 +08:00 |
|
hiyouga
|
be61bfda93
|
add upcast_lmhead option
Former-commit-id: 7ef69a1697c11ff13e7503360e40ef36cfb1c345
|
2024-01-19 23:54:25 +08:00 |
|
hiyouga
|
1a39f529c0
|
set use_reentrant=False
Former-commit-id: efa2e27d5ef6eaeb7baa7551c651ef10ab31400c
|
2024-01-19 23:29:54 +08:00 |
|
hiyouga
|
0868d5c550
|
fix #2249
Former-commit-id: 7ec64588c541422875adfdaf5692a27d05b96cb9
|
2024-01-19 21:44:32 +08:00 |
|
hiyouga
|
384f0e7678
|
add bf16 lora option
Former-commit-id: 58e7d7ff0cf9bf30e53b3eb12576f38d31976413
|
2024-01-19 16:29:03 +08:00 |
|
hiyouga
|
9b390c4bea
|
fix function formatter
Former-commit-id: 363a87376ad8fe4149b387f7ccd60f31f2a5fdf7
|
2024-01-18 16:01:07 +08:00 |
|
hiyouga
|
42a13fec46
|
Update tuner.py
Former-commit-id: db30107385f100f88c9370abea6692ce6030a0c9
|
2024-01-18 15:06:02 +08:00 |
|
hiyouga
|
790acc4c17
|
fix templates
Former-commit-id: 382cc48b2a823b9a7d4ccf2c2a163f0e5b6e3169
|
2024-01-18 14:49:52 +08:00 |
|
hiyouga
|
b74cf27538
|
fix rm dataset
Former-commit-id: fa6f810026a59cecce813a696b2fdf15ba502fc4
|
2024-01-18 14:45:37 +08:00 |
|
hiyouga
|
ffc874ec6f
|
fix pretrain data loader
Former-commit-id: 2a812b706ecc527013e79edc504ec18a4193123d
|
2024-01-18 14:42:52 +08:00 |
|
hoshi-hiyouga
|
546d6bd0b2
|
Merge pull request #2226 from hiyouga/dev
support function calling
Former-commit-id: 69391464f0d3fb0e2ef76e6b6fac51c119d66b53
|
2024-01-18 14:31:28 +08:00 |
|
hiyouga
|
8b68ca029e
|
update readme
Former-commit-id: 11e0c732c4968b083f60a0bb6f7bb5dd5ca2ba56
|
2024-01-18 14:30:48 +08:00 |
|
hiyouga
|
502f84b30c
|
add tool hint
Former-commit-id: 64734ffe2f45f80a1e33c2a72330b2ab1e58feb3
|
2024-01-18 13:19:09 +08:00 |
|
hiyouga
|
b7df920860
|
fix dataset
Former-commit-id: a7ce244a6d83d62f5bbecc588f1978e3791fd3b3
|
2024-01-18 12:59:30 +08:00 |
|
hiyouga
|
e4a424cb6a
|
enable cutoff len
Former-commit-id: e9513d300c338dfcae98eee7d057bfd00da2da0e
|
2024-01-18 12:25:42 +08:00 |
|
hiyouga
|
d8affd3967
|
add tool test
Former-commit-id: 639a355a9ceb2e4585b81aea71fc810f4b510776
|
2024-01-18 10:26:26 +08:00 |
|
hiyouga
|
a423274fd9
|
support function calling
Former-commit-id: 66533b3f65babf2429c92c0f8fafe4eff5e0ff63
|
2024-01-18 09:54:23 +08:00 |
|
hiyouga
|
f7329b1a0e
|
Update llamafy_internlm2.py
Former-commit-id: 3ca5915a4fcd3d28d10a47bf9f2188b5cf8393a8
|
2024-01-18 01:12:31 +08:00 |
|
hiyouga
|
48eb07c956
|
Update llamafy_internlm2.py
Former-commit-id: 69b3cb768eda57b63f47cd35e5da3a59b57b7853
|
2024-01-18 01:00:16 +08:00 |
|
hiyouga
|
636d8a886c
|
Update llamafy_internlm2.py
Former-commit-id: 1f1a7bcee5a5bb0fa17b13aa6393bfba89451dd7
|
2024-01-18 00:49:31 +08:00 |
|
hiyouga
|
97b52c7fdf
|
fix llamafy scripts
Former-commit-id: 99ff69c36767d4397a4a61e89317ec8c0c295c1e
|
2024-01-18 00:37:37 +08:00 |
|
hiyouga
|
344412e66e
|
fix llamafy_internlm2
Former-commit-id: a309375d020dedc313f3b6921fb53d932f156e8b
|
2024-01-18 00:26:14 +08:00 |
|