hoshi-hiyouga
|
519ac92803
|
[assets] update docker files (#8176)
|
2025-05-27 18:15:23 +08:00 |
|
hoshi-hiyouga
|
16e1a5097e
|
[webui] add infer extra args (#8167)
|
2025-05-27 12:04:00 +08:00 |
|
hoshi-hiyouga
|
09436c1f45
|
[webui] fix input args (#8162)
|
2025-05-27 02:05:54 +08:00 |
|
hoshi-hiyouga
|
f3a1dc8483
|
[model] add smollm2 and medgemma (#8161)
|
2025-05-26 23:19:58 +08:00 |
|
hoshi-hiyouga
|
dc8cca11b3
|
[deps] upgrade transformers (#8159)
|
2025-05-26 22:03:58 +08:00 |
|
Akshat Sehgal
|
e6f45d696b
|
feat: add smollm support (#8050)
|
2025-05-26 19:47:54 +08:00 |
|
wangzhan
|
c477ae6405
|
[api] support repetition_penalty and align presence_penalty with OpenAI Client (#7958)
|
2025-05-26 18:45:11 +08:00 |
|
hoshi-hiyouga
|
52dead8775
|
[assets] update wechat (#8156)
|
2025-05-26 18:28:02 +08:00 |
|
Kingsley
|
a9211a730e
|
[data] fix internvl plugin when using PIL images (#8129)
|
2025-05-22 01:32:59 +08:00 |
|
hoshi-hiyouga
|
763fbc294b
|
[misc] update data readme (#8128)
|
2025-05-21 22:41:18 +08:00 |
|
hoshi-hiyouga
|
b0c8ba73e0
|
[deps] update to transformers 4.52 (#8125)
|
2025-05-21 05:16:18 +08:00 |
|
hoshi-hiyouga
|
b3b2c9f1ee
|
[data] llama3 multi tool support (#8124)
|
2025-05-21 02:01:12 +08:00 |
|
hoshi-hiyouga
|
f96c085857
|
[assets] update readme (#8110)
|
2025-05-20 02:44:18 +08:00 |
|
hoshi-hiyouga
|
b83a38eb98
|
[data] qwen3 fixes (#8109)
|
2025-05-20 02:00:30 +08:00 |
|
hoshi-hiyouga
|
f3fd67a9bb
|
[model] switch to gptqmodel (#8108)
|
2025-05-19 22:25:40 +08:00 |
|
piamo
|
a6f3adf930
|
[model] update rope kwargs for yarn (#8101)
|
2025-05-19 20:07:54 +08:00 |
|
hoshi-hiyouga
|
ed2f89efaf
|
[doc] add no build isolation (#8103)
|
2025-05-19 19:25:13 +08:00 |
|
Ma, Xiaochen
|
16e26236eb
|
[trainer] fix KeyError at end of pretrain (#8099)
|
2025-05-19 18:01:26 +08:00 |
|
Biao Wang
|
89a0d10c18
|
[misc] fix cli (#8095)
Co-authored-by: wangbiao11 <wangbiao11@baidu.com>
|
2025-05-19 17:59:39 +08:00 |
|
Saiya
|
820ed764c4
|
[infer] support lora adapter for SGLang backend (#8067)
|
2025-05-16 23:33:47 +08:00 |
|
Kingsley
|
66f719dd96
|
[data] add forward compatibility for video_utils in Transformers 4.52.0 (#8077)
|
2025-05-16 17:41:04 +08:00 |
|
Eric Tang
|
130bfaf8e3
|
[data] support loading folder from remote (#8078)
|
2025-05-16 15:35:38 +08:00 |
|
Shawn Tao
|
e8a18c17e9
|
[infer] Modify vllm_infer.py to batch preprocess to avoid too much files opened error (#8051)
Co-authored-by: Kingsley <82590017+Kuangdd01@users.noreply.github.com>
|
2025-05-15 10:54:35 +08:00 |
|
hoshi-hiyouga
|
2b23c0a7a1
|
[assets] update wechat (#8057)
|
2025-05-14 18:01:48 +08:00 |
|
hoshi-hiyouga
|
ab2c05115b
|
[assets] update windows installation (#8042)
|
2025-05-13 17:01:56 +08:00 |
|
hoshi-hiyouga
|
8d472c20cb
|
[model] add seed coder and qwen3 quant models (#8039)
|
2025-05-13 15:59:55 +08:00 |
|
hoshi-hiyouga
|
845af89ea4
|
[data] fix kimi vl template (#8015)
|
2025-05-11 20:45:19 +08:00 |
|
Kingsley
|
cef3a0b2e2
|
[scripts] add video params for vllm infer (#7992)
|
2025-05-09 21:16:52 +08:00 |
|
yunhao-tech
|
865ac07491
|
[data] Avoid repetitive tool description warp (#8000)
Co-authored-by: chenyunhao <chenyunhao@wps.cn>
Co-authored-by: hoshi-hiyouga <hiyouga@buaa.edu.cn>
|
2025-05-09 21:16:37 +08:00 |
|
tpoisonooo
|
f584db50cf
|
[docs] add GraphGen (#7974)
|
2025-05-07 12:23:11 +02:00 |
|
hoshi-hiyouga
|
97e0a4cb5c
|
[misc] update liger kernel patch (#7966)
|
2025-05-06 20:32:16 +02:00 |
|
hoshi-hiyouga
|
c6bcca4c83
|
[example] update examples (#7964)
|
2025-05-06 17:24:25 +02:00 |
|
Kingsley
|
5ee9eb64d8
|
[model] add mimo7b (#7946)
|
2025-05-06 17:10:30 +02:00 |
|
hoshi-hiyouga
|
937447bd8a
|
[misc] fix qwen2 omni (#7962)
|
2025-05-06 15:39:13 +02:00 |
|
hoshi-hiyouga
|
52f25651a2
|
[model] add qwen2 omni 3b (#7945)
|
2025-05-03 16:36:51 +08:00 |
|
Eric Chen
|
75d7c35fdf
|
[assets] Warp Support README Update (#7887)
|
2025-05-02 00:08:48 +08:00 |
|
hoshi-hiyouga
|
6a584b4092
|
[hparam] add enable think argument (#7928)
|
2025-04-30 17:21:30 +08:00 |
|
hoshi-hiyouga
|
41ec928683
|
[data] fix base plugin (#7924)
|
2025-04-30 16:28:05 +08:00 |
|
hoshi-hiyouga
|
d8295cd601
|
[data] optimize qwen3 loss computation (#7923)
|
2025-04-30 16:18:00 +08:00 |
|
hoshi-hiyouga
|
a8430f4244
|
[misc] fix uv (#7913)
|
2025-04-30 07:45:03 +08:00 |
|
hoshi-hiyouga
|
072bfe29d3
|
[data] add eval_on_each_dataset arg (#7912)
|
2025-04-30 06:56:43 +08:00 |
|
hoshi-hiyouga
|
c5b1d07e7c
|
[data] replace eos token for base models (#7911)
|
2025-04-30 06:52:28 +08:00 |
|
hoshi-hiyouga
|
77c569e071
|
[data] improve mm plugin (#7910)
|
2025-04-30 06:34:28 +08:00 |
|
hoshi-hiyouga
|
ae392e054c
|
[model] add qwen3 (#7885)
|
2025-04-29 09:34:05 +08:00 |
|
Kingsley
|
369474451d
|
[data] fix qwen2.5 omni template (#7883)
|
2025-04-29 00:58:23 +08:00 |
|
hoshi-hiyouga
|
1f338deb87
|
[model] fix dsv3 leaf node (#7879)
|
2025-04-28 18:11:09 +08:00 |
|
hoshi-hiyouga
|
00b5c05946
|
[data] fix qwen2 omni plugin (#7875)
|
2025-04-28 14:22:41 +08:00 |
|
zhaop-l
|
1bd319d16c
|
[trainer] make projector trainable in freeze training (#7872)
Co-authored-by: hoshi-hiyouga <hiyouga@buaa.edu.cn>
|
2025-04-28 13:19:37 +08:00 |
|
hoshi-hiyouga
|
fcca3b0b0d
|
[data] fix minicpmo vllm infer (#7870)
|
2025-04-28 01:59:53 +08:00 |
|
Kingsley
|
035e98035c
|
fix attn patch for kimivl (#7867)
|
2025-04-27 23:12:28 +08:00 |
|