zhouwei
|
3d1b0e1864
|
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
|
45becd2a45
|
”add stop parameter in chat.py“
Former-commit-id: e529bf5bc14c72558d26f73c42076eaa9684205c
|
2024-05-06 10:10:00 +08:00 |
|
zhaonx96
|
8f1197de7e
|
Merge branch 'main' of https://github.com/zhaonx/LLaMA-Factory into dev
Former-commit-id: ec1f834905e241277fdd3f764c70eede97e9ff40
|
2024-05-06 10:09:00 +08:00 |
|
hoshi-hiyouga
|
25de4ce56a
|
Merge pull request #3578 from pha123661/main
Fix badam example argument
Former-commit-id: d6edf3d91e5d20f48938e02d96d2193ed3d50181
|
2024-05-05 23:41:58 +08:00 |
|
Oscar
|
d0597897bf
|
Fix badam example outdated argument
Former-commit-id: 29aa188cc774cb72367f706f1cd4c07bc5a9f241
|
2024-05-05 23:35:19 +08:00 |
|
hiyouga
|
4674f3baa7
|
add version and help to cli
Former-commit-id: f762f2215169b9fe55564d5600b758ddc66f9c9c
|
2024-05-05 02:44:35 +08:00 |
|
hiyouga
|
2f5f6722cf
|
fix eval scripts
Former-commit-id: fc3743d0b82c28fbff1170761139e4fa5d2a8939
|
2024-05-05 00:53:07 +08:00 |
|
hiyouga
|
7ef3788ff4
|
update webui
Former-commit-id: 17a53d25cdadd2df70a8afa0488f75bbf1918b89
|
2024-05-05 00:17:54 +08:00 |
|
hiyouga
|
f9aa74715a
|
update scripts
Former-commit-id: 1c07648c4bb4bb0c46bc0240547b46bd2835dce1
|
2024-05-04 23:05:17 +08:00 |
|
hiyouga
|
9b187b274c
|
add avg ppl
Former-commit-id: 40caeb6f0fdf76a1e2c9ca3761299d087fc643e0
|
2024-05-04 22:35:31 +08:00 |
|
hiyouga
|
68ed89f351
|
update ppl script
Former-commit-id: 07606fa4ab303f088170a569c1f86141a1b496c5
|
2024-05-04 22:13:14 +08:00 |
|
hiyouga
|
342d7da8d7
|
add cal_ppl script
Former-commit-id: 947068c11c0be00db2cecddb2c5842a0d6e2c321
|
2024-05-04 22:02:25 +08:00 |
|
hiyouga
|
6eda42eb7c
|
update readme
Former-commit-id: eaf83847ef6d89d8b70429138e73b04fd2aa3ef8
|
2024-05-04 17:01:21 +08:00 |
|
hiyouga
|
e9fe8815be
|
remove empty stream response
Former-commit-id: 070d0da928b1e974a094279a2782201016d2a3ab
|
2024-05-04 16:13:52 +08:00 |
|
hiyouga
|
9381fecca7
|
fix async stream api response
Former-commit-id: d70bbcae6513e50aa6094f2d98c4aa5c6641ea02
|
2024-05-04 16:11:18 +08:00 |
|
hiyouga
|
efa9140577
|
update api and support abort eval in webui
Former-commit-id: 8661bed68812e9ded9439e8a821b1d7716bc797b
|
2024-05-04 15:59:15 +08:00 |
|
hiyouga
|
b1b18b2c5a
|
update readme
Former-commit-id: 5061f7196a3278af5ebce77249d9c3c0f8a55b34
|
2024-05-04 00:43:53 +08:00 |
|
hiyouga
|
37bcbf72b4
|
update readme and webui launch
Former-commit-id: c66ffa57323ef6ea78a9b75ec5122d9ea25fd420
|
2024-05-04 00:43:02 +08:00 |
|
hiyouga
|
99125c8825
|
update readme
Former-commit-id: 012e5b9625682a628a0b7fb5879097be7166c7be
|
2024-05-04 00:31:02 +08:00 |
|
hiyouga
|
182b974786
|
fix eval in webui
Former-commit-id: 774ef2bf5823d68b9cc254a676f5adb4af533d75
|
2024-05-04 00:19:19 +08:00 |
|
hiyouga
|
7a4a6a5522
|
fix webui resume
Former-commit-id: c2f6582ddd365bb64b72e8057cc4ecd7884d2480
|
2024-05-03 23:15:19 +08:00 |
|
hiyouga
|
2383e5440c
|
fix slow op in dpo/orpo trainer
Former-commit-id: 38cad0896ea0516de6d4b2759ec9d45ee67d339b
|
2024-05-03 23:06:52 +08:00 |
|
hiyouga
|
1fea91736a
|
fix callback log multigpu #3559
Former-commit-id: 1f105f1551b12675ca7d339ef5f91333f0371987
|
2024-05-03 21:24:27 +08:00 |
|
hiyouga
|
09d9fb28f9
|
enable tqdm in webui
Former-commit-id: 1737bff64799047a5b715fd979b4c038ae213bb3
|
2024-05-03 04:42:50 +08:00 |
|
hiyouga
|
57c6eabf83
|
fix gen_args
Former-commit-id: c3e2f4f07b7fb3b1d7d2b44451660f082a467aed
|
2024-05-03 04:24:50 +08:00 |
|
hiyouga
|
33d440b577
|
fix colab gradio
Former-commit-id: 26179a29d3400d1fea155e325a79473a8bc12f04
|
2024-05-03 03:54:46 +08:00 |
|
hiyouga
|
ce8200ad98
|
update webui and add CLIs
Former-commit-id: 1368dda22ab875914c9dd86ee5146a4f6a4736ad
|
2024-05-03 02:58:23 +08:00 |
|
hiyouga
|
2cedb59bee
|
Update prepare.sh
Former-commit-id: 5928b869251a984a085289ca6861a9731dc5b910
|
2024-05-02 17:16:02 +08:00 |
|
hiyouga
|
dd0b85580e
|
fix badam configs
Former-commit-id: 8a4e6a4c65a9a42e6501b0d3ce81d6220c287454
|
2024-05-02 02:47:04 +08:00 |
|
hoshi-hiyouga
|
cd4dad846b
|
Merge pull request #3487 from codemayq/main
support BAdam in WebUI
Former-commit-id: 6eada1a2844a2b2c8aad599ebfcc35b376c938ea
|
2024-05-02 02:38:01 +08:00 |
|
hoshi-hiyouga
|
a11a04a24f
|
Update train.py
Former-commit-id: 16f0d0056967872e02969fdd842a381f9484af8a
|
2024-05-02 02:21:27 +08:00 |
|
hoshi-hiyouga
|
eb99999ca8
|
Update README_zh.md
Former-commit-id: 1c673d89faca3160627009fcd0a4aa39138570c0
|
2024-05-02 02:14:55 +08:00 |
|
hoshi-hiyouga
|
ea58cf111e
|
Update README.md
Former-commit-id: 4fb43b0c9aa48242126252ad755a2a1683b38d6a
|
2024-05-02 02:13:46 +08:00 |
|
zhaonx
|
2d95127c33
|
"add support for vllm api stop parameter"
Former-commit-id: b9f21fa639b66db09c79404d885661c96bdf9395
|
2024-04-30 17:17:09 +08:00 |
|
Lao
|
57fcdca336
|
Update README_zh.md
Former-commit-id: bacc8588dc7b0b43c240189ecf4336bedc299357
|
2024-04-28 23:31:37 +08:00 |
|
khazic
|
3d88589c0f
|
Upgrade the second sharegpt format
Former-commit-id: 057f992a666b029d207a3dc7dfc353f9abcf8316
|
2024-04-28 14:30:05 +08:00 |
|
khazic
|
dfd153cc81
|
added the second sharegpt format
Former-commit-id: 6d140ac98a78ecc0a713842bb917dc8eb14450cb
|
2024-04-28 14:27:45 +08:00 |
|
codingma
|
7641a214d8
|
support BAdam in WebUI
Former-commit-id: 1247154dd7d5eba5d11c4bb8504bf551ab49eb72
|
2024-04-28 11:31:34 +08:00 |
|
hiyouga
|
3cef844079
|
fix setup
Former-commit-id: 7d3e7db46a5f8672dd57fa5fcc03822e175047f9
v0.7.0
|
2024-04-28 03:49:13 +08:00 |
|
hiyouga
|
4dcd47100d
|
fix llava rlhf
Former-commit-id: f6863cbbcbf960d6481296c6cae3e40fd70e4e14
|
2024-04-28 03:01:49 +08:00 |
|
hiyouga
|
a412b4ed4a
|
add models to 0.7.0
Former-commit-id: 436d3754452f839c617839ab3bbaacc4a8908e19
|
2024-04-28 01:50:30 +08:00 |
|
hiyouga
|
544a6259b6
|
update readme
Former-commit-id: c9190fe36f511c3a5149d45c85a10b02a57fa88a
|
2024-04-26 23:39:19 +08:00 |
|
hiyouga
|
c501f377dd
|
release v0.7.0
Former-commit-id: 45bb89cb4d26a6b3fb5360bc90ab950738fe4920
|
2024-04-26 23:18:00 +08:00 |
|
hiyouga
|
cb8b8f40cd
|
update readme
Former-commit-id: f3d4b46338d4d484b205d0651a1fa7b2e77a1654
|
2024-04-26 20:09:14 +08:00 |
|
hiyouga
|
70bed8ad8f
|
support Qwen1.5 110B
Former-commit-id: d6e5ecaf4109127bab24e39a0696076bceb0b37c
|
2024-04-26 19:59:22 +08:00 |
|
hiyouga
|
51f776ae2a
|
fix llava qlora
Former-commit-id: 01c5a669f6fe598aac1758a700a7607da37db1bc
|
2024-04-26 18:00:23 +08:00 |
|
hiyouga
|
697bc20941
|
add llava to llamaboard
Former-commit-id: deaaff0a9de0eef9691991c99cd797461b1165cc
|
2024-04-26 06:41:35 +08:00 |
|
hiyouga
|
1480e3a88f
|
update readme
Former-commit-id: df1155245d3f71ba4f3361d43aa662ab3b024de8
|
2024-04-26 05:49:26 +08:00 |
|
hoshi-hiyouga
|
19029d5b0f
|
Merge pull request #3454 from hiyouga/mllm
Support fine-tuning LLaVA-1.5 MLLM @BUAADreamer
Former-commit-id: c4195d1e26349795f7aad5c10a8a9e2abb7b64a3
|
2024-04-26 05:46:29 +08:00 |
|
hiyouga
|
7773ac0ead
|
update readme
Former-commit-id: 41728fd74de7bec0cc6135aef9dfa3ae9fe7af73
|
2024-04-26 05:44:30 +08:00 |
|