marko1616
|
952b785bb3
|
change default_system accroding to official template
Former-commit-id: 7ad9029c5e77a87a7c324b8f90b4f80a31a5c78b
|
2024-04-15 20:45:46 +08:00 |
|
marko1616
|
72dd676208
|
Revert "Add support for function call(Not strictly following origin)"
This reverts commit dfaa31e99173cc96be65a78c5931a16e002dd929 [formerly 44f3ada4e394c06b0d972329ed2a62d2be2ea0c6].
Former-commit-id: fac9cc6e01dd8f3bc449b656804476e1871326f0
|
2024-04-15 20:27:09 +08:00 |
|
marko1616
|
dfaa31e991
|
Add support for function call(Not strictly following origin)
Former-commit-id: 44f3ada4e394c06b0d972329ed2a62d2be2ea0c6
|
2024-04-15 20:16:52 +08:00 |
|
hoshi-hiyouga
|
0c80751e87
|
Merge pull request #3276 from liu-zichen/fix_mixtral
fix: turn on output_router_logits of mixtral
Former-commit-id: 07bbaf5c67d00a152e5304e81b15fd9189e7bb99
|
2024-04-15 15:38:16 +08:00 |
|
hiyouga
|
9338f878a3
|
fix #3273
Former-commit-id: 3b20c89b342a068356ffc29c3724b645775c65db
|
2024-04-15 15:32:58 +08:00 |
|
liuzc
|
fde3d91242
|
fix: mixtral output_router_logits
Former-commit-id: ab3171ea97ec968b972287287ef9ee2502c6d37c
|
2024-04-15 12:11:49 +08:00 |
|
marko1616
|
0dcc9e0bca
|
Typo fix
Former-commit-id: 607625497738b2c8be736be7b0bd5c6f4cbaad5e
|
2024-04-13 17:30:21 +08:00 |
|
marko1616
|
aeec78b35c
|
Typo fix
Former-commit-id: 51b1e49e288e66c1b0c24ac070201c988fb2a389
|
2024-04-13 07:52:11 +08:00 |
|
marko1616
|
c991654cb4
|
Add c4ai-command-r-plus link
Former-commit-id: acaf953ca46eca8fb378067f4ada133654e4f088
|
2024-04-13 07:32:40 +08:00 |
|
marko1616
|
f328413646
|
Add template&support(Not tested)
Former-commit-id: 60bb60c4dc30a9641ddb57a44ef126f0768566c4
|
2024-04-13 04:31:33 +08:00 |
|
hiyouga
|
5486ea09e3
|
fix model card
Former-commit-id: 920e7149bf2b559c9829aa4b11cfb6d00bbb2f9e
|
2024-04-12 17:11:59 +08:00 |
|
hiyouga
|
31bbbb6d13
|
fix #3238
Former-commit-id: 4d7e81ab4722d13bec6ca1af141f94bdc74d0883
|
2024-04-12 14:28:11 +08:00 |
|
hiyouga
|
1a77de82fa
|
set dev version
Former-commit-id: f6cc76571d2c789675883a18e0db3d0c61f33808
|
2024-04-11 20:27:34 +08:00 |
|
hiyouga
|
7468f2535c
|
release v0.6.2
Former-commit-id: f92ad0a62d957b595f6a76a5403216b163eb3d17
|
2024-04-11 20:08:51 +08:00 |
|
hiyouga
|
38e4f22605
|
Merge branch 'main' of https://github.com/hiyouga/LLaMA-Factory
Former-commit-id: 23ff02c1fd3787daf0bc6ac237c8897d02f726e4
|
2024-04-10 23:58:18 +08:00 |
|
hiyouga
|
2bc2fe7b5e
|
fix #3225
Former-commit-id: 94110ecf27c32e263f1f2ee61842a3a301b9e089
|
2024-04-10 23:57:59 +08:00 |
|
hoshi-hiyouga
|
7856f98965
|
Update adapter.py
Former-commit-id: 720fde3683529ed7e08ac27c7c4598c6bdc30d44
|
2024-04-10 00:57:51 +08:00 |
|
hoshi-hiyouga
|
e25ddef08c
|
Update adapter.py
Former-commit-id: a84b8d17dbf221259212e81931d80bcdd6284ad7
|
2024-04-10 00:57:30 +08:00 |
|
Erich Schubert
|
95a4589bbf
|
Pass additional_target to unsloth
Fixes #3200
Former-commit-id: f8f87f5b0549cba6a011749c42064047f82ba577
|
2024-04-09 17:53:40 +02:00 |
|
hiyouga
|
566d71b7a9
|
fix quant infer and qwen2moe
Former-commit-id: b75d16767f35c36e2cf2aaab8a3844135085bccf
|
2024-04-09 17:12:59 +08:00 |
|
hiyouga
|
6030a4a720
|
tiny fix
Former-commit-id: d8f1ff51d4c920d4d0aeb9d53db29d1efb733c85
|
2024-04-08 21:28:39 +08:00 |
|
hoshi-hiyouga
|
5dc0cb94d4
|
Merge pull request #3161 from hiyouga/feature/add-mediatek-model
support Breeze-7B
Former-commit-id: af92ac8b62b919a75673011a1c56832e67882ee8
|
2024-04-08 20:56:51 +08:00 |
|
codingma
|
325dafcbb0
|
add empty line
Former-commit-id: 1c6c2e611d10e9fa662e3f4e1e7d23b80ae496cb
|
2024-04-07 18:28:08 +08:00 |
|
codingma
|
1a8a8b8651
|
rename template to breeze
Former-commit-id: 1223e6358dab52b4e1505057f1b16fd9d527c79e
|
2024-04-07 18:27:20 +08:00 |
|
codingma
|
75866aa020
|
rename template to breeze
Former-commit-id: 1d894e7cfb73b8a29dababb554d051bd50e4f01d
|
2024-04-07 11:39:54 +08:00 |
|
codingma
|
9e4fda326d
|
support https://github.com/hiyouga/LLaMA-Factory/issues/3152
Former-commit-id: 708f0ab4b0aa72e2c73ca36eb9ed058910e43092
|
2024-04-07 11:34:01 +08:00 |
|
sliderSun
|
1131ddfaff
|
fix spell error
Former-commit-id: e6d36a2e593ebc1193b1735075c4ddb5d9f54990
|
2024-04-07 10:59:15 +08:00 |
|
sliderSun
|
9f437b5c43
|
support Qwen1.5-32B
Former-commit-id: c419adf1697b92520342f4ffa697c84bf19ca37d
|
2024-04-07 10:56:03 +08:00 |
|
sliderSun
|
0cc03d3f05
|
support Qwen1.5-32B
Former-commit-id: 8f2c67b95a8e177eb4096382417a70cacba38e90
|
2024-04-07 10:26:13 +08:00 |
|
hiyouga
|
a246ac1914
|
tiny fix
Former-commit-id: 70aceecb27e72095c05462d01f956061669b267e
|
2024-04-04 02:19:03 +08:00 |
|
hiyouga
|
48ceac845c
|
back to gradio 4.21 and fix chat
Former-commit-id: 695734a40a702ea059d855da54080cc8d161e41a
|
2024-04-04 02:07:20 +08:00 |
|
hiyouga
|
b1986a06b9
|
fix bug in latest gradio
Former-commit-id: 44a962862b4a74e50ef5786c8d5719faaa65f63f
|
2024-04-04 00:55:31 +08:00 |
|
hiyouga
|
43d134ba29
|
fix requires for windows
Former-commit-id: 5e25fae40b7ea9cfa72717efbe3677199ca9608f
|
2024-04-03 21:56:43 +08:00 |
|
hiyouga
|
1348f7d860
|
fix resize vocab at inference #3022
Former-commit-id: c243720b89eec0af2872fa3c7980a0026d893f4d
|
2024-04-03 18:14:24 +08:00 |
|
hiyouga
|
f6530222f7
|
fix #3116
Former-commit-id: b7256aa33d761280751518c20f29f9b8ea3fb025
|
2024-04-03 14:47:59 +08:00 |
|
hiyouga
|
b12176d818
|
simplify readme
Former-commit-id: 0da6ec2d516326fe9c7583ba71cd1778eb838178
|
2024-04-02 20:07:43 +08:00 |
|
hiyouga
|
117b67ea30
|
add moe aux loss control #3085
Former-commit-id: c9187ebc944e2de454ace3304b7d28eabb1b1a81
|
2024-04-02 14:26:31 +08:00 |
|
hiyouga
|
03e20bb5c6
|
fix #3022
Former-commit-id: dac2f617bda9470ac8d85c7e9def09cc04970506
|
2024-04-02 13:58:39 +08:00 |
|
hiyouga
|
9e14501edb
|
set dev version
Former-commit-id: 922ecae89210e5b8d62d78774f123a6d75c525ba
|
2024-04-01 23:24:08 +08:00 |
|
hiyouga
|
1dc963caa6
|
fix #3083
Former-commit-id: ff9a3f73961a362d0ddc22079f80a85465fffda8
|
2024-04-01 22:53:52 +08:00 |
|
hiyouga
|
85726c91ce
|
add qwen1.5 moe
Former-commit-id: 3ea94f0d12cec25ac694a2c4ae8971c356990b61
|
2024-04-01 21:49:40 +08:00 |
|
hiyouga
|
40211db275
|
fix #3077
Former-commit-id: d0340391e8075cff0d84b3ef879c2101b66ca1dc
|
2024-04-01 21:35:18 +08:00 |
|
hiyouga
|
e7f13098c6
|
support infer 4bit model on GPUs #3023
Former-commit-id: 950a9dab9055839990656b2b40956792b253573d
|
2024-04-01 17:34:04 +08:00 |
|
hiyouga
|
61eb3a3d46
|
update webui
Former-commit-id: e96d260917a35ad2068f7b28b4f0b334b808ccc2
|
2024-04-01 16:23:28 +08:00 |
|
hiyouga
|
be0a807e8c
|
fix ORPO loss
Former-commit-id: 5544ddde9087f00f9e20b78d0079f20c2f5d1604
|
2024-04-01 14:42:41 +08:00 |
|
hiyouga
|
52d402e2a9
|
fix IPO and ORPO loss
Former-commit-id: fc27955732aedbb12003faf19b760e2768b228f2
|
2024-04-01 14:37:53 +08:00 |
|
hiyouga
|
c5a46f9113
|
fix plots
Former-commit-id: 81355671296b84d438967463bb2a92934ff31aae
|
2024-03-31 19:43:48 +08:00 |
|
hiyouga
|
00e17a377c
|
use log1p in orpo loss
https://github.com/huggingface/trl/pull/1491
Former-commit-id: 3b15d495264b00a4f8716bafea334778874963d7
|
2024-03-31 19:27:08 +08:00 |
|
hiyouga
|
9abd83adb1
|
update readme
Former-commit-id: 297b01f16ac78cde15a5d85a9a5b82ea20bfaf23
|
2024-03-31 18:46:34 +08:00 |
|
hiyouga
|
1aba442bcd
|
support orpo in webui
Former-commit-id: dd5cc78d4fb18dd0a2e9d57f0f046cfe9f0dc2c9
|
2024-03-31 18:34:59 +08:00 |
|