zhouwei
|
ed5dd3b8c5
|
The training efficiency of the Ascend 910A has been significantly enhanced, leveraging the full computational power of the NPU (Neural Processing Unit) and the capabilities of torch_npu, a PyTorch library optimized for NPUs. This improvement has resulted in a remarkable tenfold increase in efficiency.
Former-commit-id: 90980b626d3408b3e2ee32a02456c20881318be7
|
2024-05-06 13:29:59 +08:00 |
|
zhaonx96
|
8b9b8f5c28
|
”add stop parameter in chat.py“
Former-commit-id: e529bf5bc14c72558d26f73c42076eaa9684205c
|
2024-05-06 10:10:00 +08:00 |
|
zhaonx96
|
63056386d5
|
Merge branch 'main' of https://github.com/zhaonx/LLaMA-Factory into dev
Former-commit-id: ec1f834905e241277fdd3f764c70eede97e9ff40
|
2024-05-06 10:09:00 +08:00 |
|
hiyouga
|
1b9308d21e
|
add version and help to cli
Former-commit-id: f762f2215169b9fe55564d5600b758ddc66f9c9c
|
2024-05-05 02:44:35 +08:00 |
|
hiyouga
|
6f6d11e66c
|
update webui
Former-commit-id: 17a53d25cdadd2df70a8afa0488f75bbf1918b89
|
2024-05-05 00:17:54 +08:00 |
|
hiyouga
|
33c2ab3bd1
|
remove empty stream response
Former-commit-id: 070d0da928b1e974a094279a2782201016d2a3ab
|
2024-05-04 16:13:52 +08:00 |
|
hiyouga
|
d59caef516
|
fix async stream api response
Former-commit-id: d70bbcae6513e50aa6094f2d98c4aa5c6641ea02
|
2024-05-04 16:11:18 +08:00 |
|
hiyouga
|
d2cdddd11e
|
update api and support abort eval in webui
Former-commit-id: 8661bed68812e9ded9439e8a821b1d7716bc797b
|
2024-05-04 15:59:15 +08:00 |
|
hiyouga
|
62953504ef
|
update readme and webui launch
Former-commit-id: c66ffa57323ef6ea78a9b75ec5122d9ea25fd420
|
2024-05-04 00:43:02 +08:00 |
|
hiyouga
|
8bbafa17bd
|
fix eval in webui
Former-commit-id: 774ef2bf5823d68b9cc254a676f5adb4af533d75
|
2024-05-04 00:19:19 +08:00 |
|
hiyouga
|
b62a3a8e5d
|
fix webui resume
Former-commit-id: c2f6582ddd365bb64b72e8057cc4ecd7884d2480
|
2024-05-03 23:15:19 +08:00 |
|
hiyouga
|
b3a4dcb2dc
|
fix slow op in dpo/orpo trainer
Former-commit-id: 38cad0896ea0516de6d4b2759ec9d45ee67d339b
|
2024-05-03 23:06:52 +08:00 |
|
hiyouga
|
4dfe10982d
|
fix callback log multigpu #3559
Former-commit-id: 1f105f1551b12675ca7d339ef5f91333f0371987
|
2024-05-03 21:24:27 +08:00 |
|
hiyouga
|
689912d32c
|
enable tqdm in webui
Former-commit-id: 1737bff64799047a5b715fd979b4c038ae213bb3
|
2024-05-03 04:42:50 +08:00 |
|
hiyouga
|
a340785c6a
|
fix gen_args
Former-commit-id: c3e2f4f07b7fb3b1d7d2b44451660f082a467aed
|
2024-05-03 04:24:50 +08:00 |
|
hiyouga
|
5fd6199ef8
|
fix colab gradio
Former-commit-id: 26179a29d3400d1fea155e325a79473a8bc12f04
|
2024-05-03 03:54:46 +08:00 |
|
hiyouga
|
419a3849f2
|
update webui and add CLIs
Former-commit-id: 1368dda22ab875914c9dd86ee5146a4f6a4736ad
|
2024-05-03 02:58:23 +08:00 |
|
hiyouga
|
c5c52dfc50
|
fix badam configs
Former-commit-id: 8a4e6a4c65a9a42e6501b0d3ce81d6220c287454
|
2024-05-02 02:47:04 +08:00 |
|
hoshi-hiyouga
|
3aae4df30c
|
Update train.py
Former-commit-id: 16f0d0056967872e02969fdd842a381f9484af8a
|
2024-05-02 02:21:27 +08:00 |
|
zhaonx
|
e22af297ee
|
"add support for vllm api stop parameter"
Former-commit-id: b9f21fa639b66db09c79404d885661c96bdf9395
|
2024-04-30 17:17:09 +08:00 |
|
codingma
|
812aceb1d5
|
support BAdam in WebUI
Former-commit-id: 1247154dd7d5eba5d11c4bb8504bf551ab49eb72
|
2024-04-28 11:31:34 +08:00 |
|
hiyouga
|
c52cab3e40
|
fix llava rlhf
Former-commit-id: f6863cbbcbf960d6481296c6cae3e40fd70e4e14
|
2024-04-28 03:01:49 +08:00 |
|
hiyouga
|
d87d442499
|
add models to 0.7.0
Former-commit-id: 436d3754452f839c617839ab3bbaacc4a8908e19
|
2024-04-28 01:50:30 +08:00 |
|
hiyouga
|
190ae7b73d
|
release v0.7.0
Former-commit-id: 45bb89cb4d26a6b3fb5360bc90ab950738fe4920
|
2024-04-26 23:18:00 +08:00 |
|
hiyouga
|
9a92854f1a
|
support Qwen1.5 110B
Former-commit-id: d6e5ecaf4109127bab24e39a0696076bceb0b37c
|
2024-04-26 19:59:22 +08:00 |
|
hiyouga
|
9d1a4b5158
|
fix llava qlora
Former-commit-id: 01c5a669f6fe598aac1758a700a7607da37db1bc
|
2024-04-26 18:00:23 +08:00 |
|
hiyouga
|
9c660479b8
|
add llava to llamaboard
Former-commit-id: deaaff0a9de0eef9691991c99cd797461b1165cc
|
2024-04-26 06:41:35 +08:00 |
|
hiyouga
|
3058b4769c
|
update readme
Former-commit-id: 41728fd74de7bec0cc6135aef9dfa3ae9fe7af73
|
2024-04-26 05:44:30 +08:00 |
|
hiyouga
|
a635030931
|
support mllm hf inference
Former-commit-id: 2c7c01282acd7ddabbb17ce3246b8dae4bc4b8cf
|
2024-04-26 05:34:58 +08:00 |
|
hoshi-hiyouga
|
8b40dcab87
|
Update preprocess.py
Former-commit-id: 0e376eab23d38b8fca05f054f3cde308756ee3b1
|
2024-04-26 04:10:28 +08:00 |
|
hoshi-hiyouga
|
4f70919405
|
Update aligner.py
Former-commit-id: 855489074c469f47572153df0fa1e251b187b232
|
2024-04-26 03:48:34 +08:00 |
|
hoshi-hiyouga
|
b2f80deabe
|
Update parser.py
Former-commit-id: 4df75e8a9a391565cc3eec69bc0ebf5d5192de61
|
2024-04-26 03:35:39 +08:00 |
|
hoshi-hiyouga
|
5153324db6
|
Update loader.py
Former-commit-id: 6a5f2e2ab7304113ff71cb77aafff6a1f74831f8
|
2024-04-26 03:33:07 +08:00 |
|
hoshi-hiyouga
|
07f1dcb0a8
|
Update workflow.py
Former-commit-id: 5b8b5b975716d539ae2fae8536f79e106aa0b566
|
2024-04-26 03:29:12 +08:00 |
|
hoshi-hiyouga
|
651fdb819c
|
Update loader.py
Former-commit-id: 72d4817a15f6916706828ea2a61d808183c23773
|
2024-04-26 03:22:40 +08:00 |
|
hoshi-hiyouga
|
a594aef320
|
update hparam name
Former-commit-id: 9941adfbf06db37f8ba32c4555f6e58e27188aaf
|
2024-04-26 02:49:39 +08:00 |
|
hoshi-hiyouga
|
1dcb65ec11
|
delete llava template (use vicuna)
Former-commit-id: 420e64970e5a0e45453041927e0366ee8beb73d5
|
2024-04-26 02:20:47 +08:00 |
|
BUAADreamer
|
33d22d57c1
|
modify some bug
Former-commit-id: 593b7b004df74bd24361c9883401a656c08fb589
|
2024-04-25 22:59:46 +08:00 |
|
BUAADreamer
|
7e369fd58e
|
modify some style
Former-commit-id: 1291c7ee39361dd75247c67f04dcf20b472faf83
|
2024-04-25 22:40:53 +08:00 |
|
BUAADreamer
|
8506eeac13
|
modify some style
Former-commit-id: d578a90cefa7ec813355795bdd6ead5ee558ce26
|
2024-04-25 22:40:25 +08:00 |
|
BUAADreamer
|
745e597360
|
merge some func
Former-commit-id: 3085107c44715e4b2ca96d73b20d90c172b95219
|
2024-04-25 22:35:17 +08:00 |
|
BUAADreamer
|
ec8c1d7d48
|
modify some style
Former-commit-id: 053062abc007014a7fde95c5ae9f4d859893d8ad
|
2024-04-25 22:04:09 +08:00 |
|
BUAADreamer
|
62d9d20686
|
modify some style
Former-commit-id: b016e6a671a2f228f0bdd9b8d5995b4669609655
|
2024-04-25 21:58:18 +08:00 |
|
BUAADreamer
|
633e76a1bd
|
modify style
Former-commit-id: c1f1df99e4dc3d0aadf1207b4e9a16218187fd5a
|
2024-04-25 21:29:50 +08:00 |
|
BUAADreamer
|
a79a8cd0a5
|
modify style
Former-commit-id: 3bffc1e1b8bcc4582cebea06d35e5146163c7bec
|
2024-04-25 21:27:48 +08:00 |
|
BUAADreamer
|
bb46c64dd6
|
modify style
Former-commit-id: 54b713d0c4ffdfc6a7faeb14471b58bb1cd8acf5
|
2024-04-25 21:15:16 +08:00 |
|
BUAADreamer
|
02a87c5bd2
|
Merge branch 'main' of https://github.com/BUAADreamer/LLaMA-Factory
Former-commit-id: c4bb5af69c5bbf0b1ea044cbb2b18acddc6733ac
|
2024-04-25 21:08:40 +08:00 |
|
BUAADreamer
|
c11c9711e7
|
add some
Former-commit-id: 8d035a849c4a441d457791aab073861adf69a09f
|
2024-04-25 21:08:32 +08:00 |
|
hiyouga
|
3aecfe2a7f
|
add webui backend option
Former-commit-id: 3764586cb3ed64fe376d0ae420ff5690c28459e2
|
2024-04-25 20:49:23 +08:00 |
|
hiyouga
|
b9d2e1e6cf
|
vllm + lora support
Former-commit-id: 8cb86ba355195f5d6dcb95ee6b6b7203463a34db
|
2024-04-25 20:24:31 +08:00 |
|