2872 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Butui Hu	83688b0b4d	[launcher] Add elastic and fault-tolerant training support (#8286) ... Signed-off-by: Butui Hu <hot123tea123@gmail.com>	2025-06-05 16:40:03 +08:00
Kingsley	5308424705	[script] add Script description for qwen_omni_merge (#8293)	2025-06-05 13:22:01 +08:00
Yaowei Zheng	81c4d9bee6	[assets] update docker files (#8291)	2025-06-04 23:30:46 +08:00
Yaowei Zheng	ee676d29f6	[assets] update readme (#8288)	2025-06-04 17:46:12 +08:00
Yaowei Zheng	e3d5e0fa28	[assets] add icon (#8276)	2025-06-03 20:36:21 +08:00
Kingsley	3425bc6e71	[data] support nested images input for videos (#8264)	2025-06-03 20:26:29 +08:00
Ze-Yi LIN	6cc247e815	[tracking] swanlab add llamafactory tag (#8258)	2025-06-03 18:42:29 +08:00
Yaowei Zheng	16a3f8a71b	[assets] update wechat (#8270)	2025-06-03 17:33:57 +08:00
Kingsley	65aa86ed39	[model] add MIMO_VL (#8249)	2025-06-01 03:54:54 +08:00
Yaowei Zheng	fba9c9d9b9	[deps] upgrade transformers to 4.52.4 (#8245)	2025-05-31 16:51:40 +08:00
Akshat Sehgal	21829b5eaf	[model] add smollm2 support (#8220)	2025-05-31 16:29:01 +08:00
hoshi-hiyouga	762c2d776f	[assets] update readme (#8235)	2025-05-30 16:52:12 +08:00
Kingsley	e31afdfd4f	[scripts] specify model class for qwen_omni merge (#8227)	2025-05-30 14:20:12 +08:00
hoshi-hiyouga	be02003d16	[model] add deepseek 0528 models (#8215)	2025-05-29 21:37:07 +08:00
hoshi-hiyouga	a4048b7bb6	[assets] fix docker images (#8203)	2025-05-28 22:26:05 +08:00
yzoaim	73b12baaaf	[workflow] auto push docker images (#8181) ... Co-authored-by: hoshi-hiyouga <hiyouga@buaa.edu.cn>	2025-05-28 20:21:15 +08:00
hoshi-hiyouga	55d37dc472	[assets] update Dockerfile (#8201)	2025-05-28 20:20:59 +08:00
hoshi-hiyouga	54ffd06026	[webui] fix skip args (#8195)	2025-05-28 18:11:07 +08:00
Muqi Li	00c4988f89	[assets] fix incorrect user_tag in dataset_info.json to prevent skipped entries (#8197)	2025-05-28 18:01:37 +08:00
Youngwoo Kim	57c6e23247	[data] Reading files from cloud is broken (#8182) (#8183)	2025-05-28 15:50:44 +08:00
hoshi-hiyouga	07f792148e	[assets] fix docker image (#8180)	2025-05-27 19:01:31 +08:00
hoshi-hiyouga	e542f95710	[data] fix shared file system (#8179)	2025-05-27 18:36:03 +08:00
hoshi-hiyouga	4ecf4daeb2	[webui] add extra args to export (#8178)	2025-05-27 18:25:31 +08:00
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