hiyouga
98fb3d015a
fix #4419
...
Former-commit-id: 15069c3ca814d5ac9beec77d914b71cde7ea0f47
2024-06-25 01:51:29 +08:00
hoshi-hiyouga
bfb2ad7c79
Merge pull request #4352 from Ledzy/main
...
[Enhancement] Support ZeRO-3 when using BAdam
Former-commit-id: 0dc75275efa7d7540b472783a52ea6aeaa503c0b
2024-06-25 01:49:13 +08:00
hiyouga
135bfbf7c1
tiny fix
...
Former-commit-id: bb57478366a70a0871af30ab31c890f471e27ff4
2024-06-25 01:15:19 +08:00
hoshi-hiyouga
c6b17ebc20
Merge pull request #4355 from MengqingCao/npu
...
Add docker-npu
Former-commit-id: 2a59806352713764b1e4b7a54942466f972f5fdc
2024-06-25 01:07:43 +08:00
hoshi-hiyouga
b55eb30474
Update README_zh.md
...
Former-commit-id: f0c95160fea48b8c6291f42beb79ac089177fbb2
2024-06-25 01:06:59 +08:00
hoshi-hiyouga
cec2f1fc00
Update README.md
...
Former-commit-id: abe7aca5e133960da9200e3a036d9a550f474171
2024-06-25 01:03:38 +08:00
hoshi-hiyouga
8367ec03a7
Update docker-compose.yml
...
Former-commit-id: e038daf8dfa5d948b70c18469cb5a0be9aec464a
2024-06-25 00:54:28 +08:00
hoshi-hiyouga
37013f8068
Update Dockerfile
...
Former-commit-id: cdcd9455c19311394e148476a28ca75849c845b2
2024-06-25 00:50:34 +08:00
hoshi-hiyouga
8360544d65
Update docker-compose.yml
...
Former-commit-id: 56af208074e6af5465183af85367e7edd89d5aa6
2024-06-25 00:46:47 +08:00
hoshi-hiyouga
b5cdef43a1
Update Dockerfile
...
Former-commit-id: c897a70501707c0f4c432bb8e9a9beeb4e8953a3
2024-06-25 00:46:08 +08:00
hoshi-hiyouga
2e5d521ed8
Update Dockerfile
...
Former-commit-id: 632681d8ece0eaac59bb364d971435a3bc6665a9
2024-06-24 23:41:35 +08:00
hoshi-hiyouga
dbe35d52d1
Merge pull request #4409 from kno10/patch-2
...
Print help if no arguments given
Former-commit-id: 94ff749773d9f30ee0c98872ace6b7b542fadeda
2024-06-24 23:21:31 +08:00
hoshi-hiyouga
8bcdb6f52c
Update cli.py
...
Former-commit-id: 9db6126496ec9e834541823715f700f92b3968c7
2024-06-24 23:21:10 +08:00
hoshi-hiyouga
5cfcb8262e
Merge pull request #4417 from mMrBun/main
...
Add tool_format parameter to rewrite templates for different function call formats.
Former-commit-id: 8d1460cad5bff5e4626fdd675046021e0a3d1947
2024-06-24 23:17:55 +08:00
hoshi-hiyouga
0b331a318b
Update test_formatter.py
...
Former-commit-id: d13ef043441734189b05e739dbbebb16077a6f0b
2024-06-24 23:14:36 +08:00
hoshi-hiyouga
5d6cf55208
Update template.py
...
Former-commit-id: d53517bff6f8734221d7df9982f3bdd4d2eb2cab
2024-06-24 23:12:59 +08:00
hoshi-hiyouga
9a1ec19845
Update loader.py
...
Former-commit-id: afa59d61844595e6b615227e6bfdc0b16c8015dd
2024-06-24 23:06:18 +08:00
hiyouga
a79e93f335
fix #4410
...
Former-commit-id: f49adc4ab5eade21d7a9e029212f17688ee9b0cf
2024-06-24 22:34:31 +08:00
hoshi-hiyouga
abcb94a738
Merge pull request #4445 from MengqingCao/label
...
auto-label npu issue
Former-commit-id: 87f4779e224c4d81c410a287369285b86e992c1f
2024-06-24 22:02:05 +08:00
hoshi-hiyouga
a4f2d5aa6f
Update label_issue.yml
...
Former-commit-id: dc2f7998b4ae9d7223c7c16732d835cea2a28713
2024-06-24 22:01:23 +08:00
hoshi-hiyouga
6b738d1c89
Update label_issue.yml
...
Former-commit-id: 90785a69c6210c3a02babb12c56fb7900095247c
2024-06-24 21:59:39 +08:00
hoshi-hiyouga
f4c518b370
Merge pull request #4446 from stceum/bug-fix
...
Bug Fix: `off` is parsed as `False` in yaml file
Former-commit-id: 243478a3d6c08f5677ee57871862694561617f64
2024-06-24 21:41:28 +08:00
hoshi-hiyouga
d475dd3809
Update parser.py
...
Former-commit-id: 60e605cd9d399bd04432864ede9c84302890eac8
2024-06-24 21:37:42 +08:00
hoshi-hiyouga
5675c47a01
Update test_attention.py
...
Former-commit-id: c2cc7a0f152aa14fc03ae413f4a9dc06742a29d7
2024-06-24 21:35:34 +08:00
stceum
16e950454e
Bug Fix: off is parsed as False in yaml file, changed to disabled to avoid this.
...
Former-commit-id: 171289d8e4c111fdca2b100282b64c74a04a4726
2024-06-24 20:39:31 +08:00
MengqingCao
2926265a14
auto-label npu issue
...
Former-commit-id: d19c9eac783377151e58731723fb7cbb2dab3323
2024-06-24 12:27:00 +00:00
MengqingCao
af2607de1a
update docker files
...
1. add docker-npu (Dockerfile and docker-compose.yml)
2. move cuda docker to docker-cuda and tiny changes to adapt to the new path
Former-commit-id: 5431c1f18aadb072208efe7fd8e36fdcfbf807c2
2024-06-24 10:57:36 +00:00
hiyouga
826d7808b4
update readme
...
Former-commit-id: 0775d56ee3cfde34e28a48cbf4a583f4530def19
2024-06-24 18:29:04 +08:00
hiyouga
4c89aca243
update readme
...
Former-commit-id: a1477208471039d3578980f929f1ca8c2a07aa96
2024-06-24 18:22:12 +08:00
mMrBun
43a065bb07
Add tool_format to overwrite tool formatter template
...
Former-commit-id: af08971ca50443fd5597e5e4412a3aa17214502f
2024-06-22 02:13:23 +08:00
hiyouga
4513a2cc75
remove dup template
...
Former-commit-id: 5fec12203b24608af4d4993f44a657eb5a0348e5
2024-06-22 01:31:32 +08:00
hiyouga
f29c1ac6e5
fix api
...
Former-commit-id: dcbd6d86dfc49f12529b02ec331e3e5c05740061
2024-06-22 00:00:38 +08:00
Erich Schubert
05abe47c8b
Print help if no arguments given
...
Former-commit-id: 08dfb7ec636fd5bfbb30dac9d5fba6e32bfc6728
2024-06-21 09:14:21 +02:00
ancv
6c185a2c57
move configure_packing to llamafactory.model.patcher and fix constants
...
Former-commit-id: 9c5e972c9c81957f2e9e30bf284ef1c076de9fd0
2024-06-21 00:45:06 +07:00
hiyouga
af2cb33bb2
tiny fix
...
Former-commit-id: 2d8d47f6126d68db1701ed18fc31310c6f14dd49
2024-06-20 22:56:05 +08:00
hoshi-hiyouga
f16a4a8264
Merge pull request #4382 from MengqingCao/bugfix
...
upper bound numpy version to <2.0
Former-commit-id: 07a0182cd470132fafe07b8ea1951c9672d0eb87
2024-06-20 10:19:37 +08:00
MengqingCao
b232552d42
update dependencies
...
Former-commit-id: 25164273d1ca7a8f6f99b41279e342906f6bc4d5
2024-06-20 02:09:47 +00:00
hiyouga
0edccc11a5
improve llamaboard
...
Former-commit-id: e606ab35c0eced667dde7137c2d72848f264c96c
2024-06-19 23:46:03 +08:00
hiyouga
b2f5c0e0db
fix llamaboard abort
...
Former-commit-id: 9ef609a2c0185040e531dea3829a6f481539cdea
2024-06-19 23:22:28 +08:00
hiyouga
5f5d4c1923
update patcher
...
Former-commit-id: afb365e515d615dd62f791622450debab60ce5cc
2024-06-19 21:27:00 +08:00
hiyouga
a7d7f79855
set dev version
...
Former-commit-id: 221665345d97f839ce4ba8d54643da30c71b6083
2024-06-19 21:08:16 +08:00
hiyouga
f0bff18324
Update publish.yml
...
Former-commit-id: 60b0633e29c9e701aa3813bd1fdc0282bd07f7c8
2024-06-19 20:46:33 +08:00
hiyouga
b631bdc5b7
release v0.8.2
...
Former-commit-id: 3050bbe51d46acd8473275d2713fc28932e4a3d3
2024-06-19 20:42:09 +08:00
hiyouga
c65f7e9bd5
fix jinja template
...
Former-commit-id: 0ebf2e2ee23918d28b0cbb20ba456732d6eedfbb
2024-06-19 20:03:50 +08:00
hiyouga
3e0fa4a8da
fix templates
...
Former-commit-id: 6f357d59b73309c5955683008632e7f320e7dcb1
2024-06-19 17:44:05 +08:00
Jonery
fa3150548e
Cleaner integration.
...
Former-commit-id: 26d4b05d424bd71f570195dd433258caf6465d92
2024-06-19 12:29:40 +08:00
hiyouga
235ed85b0f
fix bug
...
Former-commit-id: 412139eaa2fde98ba19e1257d21144382a59f0d6
2024-06-19 03:49:23 +08:00
hiyouga
1ca639a777
use prefix to replace force system
...
Former-commit-id: 731d9a964f1c3dbfb83825524d697831e691fb9d
2024-06-19 03:39:52 +08:00
hiyouga
e36a994fe6
fix tool formatter, allow parallel function #4362
...
Former-commit-id: b8f16c976db4ecec1cc8558851c8cbfb6a5b7e9c
2024-06-19 03:23:51 +08:00
hoshi-hiyouga
19ffcfea76
Merge pull request #4173 from mMrBun/main
...
Implemented the tool_formatter and tool_extractor for glm4 and Qwen2 tool_format
Former-commit-id: 36b02ceed40198ecd5d559ee4ebef9205442ded2
2024-06-19 03:18:55 +08:00
