Commit Graph

  • 07aa7b71a3 [misc] update readme (#6917) hoshi-hiyouga 2025-02-13 00:58:10 +08:00
  • 1679930e00 [breaking change] refactor data pipeline (#6901) hoshi-hiyouga 2025-02-13 00:39:20 +08:00
  • d50e04b805 [misc] support for launching LLaMA-Factory with uv run (#6907) Eric Tang 2025-02-12 08:38:44 -08:00
  • e515fe62de [example] fix path to ray example (#6906) Eric Tang 2025-02-12 08:29:32 -08:00
  • 036fb0d561 [misc] fix grad ckpt func (#6916) hoshi-hiyouga 2025-02-13 00:17:18 +08:00
  • bae934dea3 [trainer] fix llama3.2 vision kto train (#6904) marko1616 2025-02-12 19:09:14 +08:00
  • 2e2f6bea07 [data] feat: auto template (#6905) hoshi-hiyouga 2025-02-12 00:22:53 +08:00
  • 1b02183da9 [misc] update readme (#6903) hoshi-hiyouga 2025-02-11 22:51:26 +08:00
  • 197aa3baf4 [data] fix ollama template (#6902) hoshi-hiyouga 2025-02-11 22:43:09 +08:00
  • c6be9e242c [misc] support export ollama modelfile (#6899) hoshi-hiyouga 2025-02-11 19:52:25 +08:00
  • 2e954d8fd2 [data] refactor template (#6896) hoshi-hiyouga 2025-02-11 17:59:25 +08:00
  • fafa3add84 support ollama modelfile export (#4686) codingma 2025-02-11 17:52:24 +08:00
  • 593acca556 [data] refactor mm plugin (#6895) hoshi-hiyouga 2025-02-11 16:34:49 +08:00
  • 188f22d8a7 [data] fix qwen_2_5_vl video processing (#6868) HJ 2025-02-11 16:14:50 +08:00
  • 703bb9cc18 [assets] update wechat (#6892) hoshi-hiyouga 2025-02-11 13:56:26 +08:00
  • 5433b318bb [da'ta] fix minicpmv plugin (#6890) Zhangchi Feng 2025-02-11 13:30:44 +08:00
  • fe4f4e9758 [data] fix: sharegpt converter (#6879) HJ 2025-02-10 21:59:12 +08:00
  • 1bb3d17d9e [data] fix mllama collator (#6874) hoshi-hiyouga 2025-02-09 22:42:25 +08:00
  • b93333685b [test] align test cases (#6865) hoshi-hiyouga 2025-02-09 01:03:49 +08:00
  • fcd0f0480d [dataset] add openthought (#6866) hoshi-hiyouga 2025-02-09 00:53:01 +08:00
  • ff6658ad27 [deps] upgrade vllm (#6857) hoshi-hiyouga 2025-02-08 15:02:28 +08:00
  • 28037c7834 fix qwen2vl plugin (#6855) hoshi-hiyouga 2025-02-08 10:59:10 +08:00
  • f70208e1c0 [misc] allow extra args (#6831) hoshi-hiyouga 2025-02-06 12:38:08 +08:00
  • 7aa9767dc2 [assets] update wechat (#6830) hoshi-hiyouga 2025-02-06 12:02:05 +08:00
  • 01915eaf40 [model] support audio (#6701) Zhangchi Feng 2025-02-05 04:59:09 +08:00
  • e665e1fed5 [data] allow thought in function call (#6797) Yueqi Song 2025-02-05 02:26:23 +08:00
  • 1fee69f874 [misc] update license year & fix llama pro (#6814) hoshi-hiyouga 2025-02-05 01:53:33 +08:00
  • 8504bde893 [data] fix qwen tool template (#6796) Yueqi Song 2025-02-05 00:02:00 +08:00
  • 85f22d01bf [data] fix minicpmv plugin (#6801) Zhangchi Feng 2025-02-04 21:20:15 +08:00
  • 822d5d362c [assets] update wechat (#6810) hoshi-hiyouga 2025-02-04 21:17:40 +08:00
  • 32163e7ce0 [readme] update flash attention installation instruction on win platform (#6788) neavo 2025-02-01 12:43:29 +08:00
  • 454140d912 [misc] update workflows (#6787) hoshi-hiyouga 2025-02-01 04:54:42 +08:00
  • 445d643ef3 [model] add mistral small models (#6786) hoshi-hiyouga 2025-02-01 04:31:38 +08:00
  • e8c1979b79 [model] add qwen2.5 vl models (#6779) hoshi-hiyouga 2025-01-31 03:00:29 +08:00
  • f6779b0e0c [breaking] support transformers 4.48 (#6628) hoshi-hiyouga 2025-01-31 01:36:33 +08:00
  • 245de012ca [webui] improve webui & reasoning mode (#6778) hoshi-hiyouga 2025-01-31 00:09:21 +08:00
  • f143360ee6 [assets] update wechat (#6771) codingma 2025-01-29 12:31:24 +08:00
  • f5350b103b [model] add deepseek-R1 & show think process (#6767) qvlehao 2025-01-29 12:16:26 +08:00
  • aa7c07caf0 fix: avoid redundant normalization in DPO's SFT loss calculation (#6722) yinpu 2025-01-21 13:38:02 +08:00
  • 324f07613a [webui] support ja (#6698) engchina 2025-01-20 19:46:38 +08:00
  • 0c59483368 [assets] update wechat (#6710) hoshi-hiyouga 2025-01-20 16:29:24 +08:00
  • 1efe525df7 [model] support yarn (#6693) hoshi-hiyouga 2025-01-18 13:56:09 +08:00
  • ee0b3b1e1a [assets] update wechat (#6692) hoshi-hiyouga 2025-01-18 12:35:03 +08:00
  • f87c788154 [misc] update mm plugin (#6691) hoshi-hiyouga 2025-01-17 23:04:26 +08:00
  • bbf334f823 disable valset by default (#6690) hoshi-hiyouga 2025-01-17 21:09:30 +08:00
  • 770433fa33 [webui] upgrade to gradio 5 (#6688) hoshi-hiyouga 2025-01-17 20:15:42 +08:00
  • 788accb601 fix qwen2 moe (#6684) hoshi-hiyouga 2025-01-17 13:46:09 +08:00
  • 555f17c1ee [data] Fix minicpmv/o dpo training (#6657) Zhangchi Feng 2025-01-15 17:30:37 +08:00
  • 8895cf1152 Update val_size english description (#6653) steveepreston 2025-01-15 11:30:20 +03:30
  • 320e40d873 update readme (#6648) hoshi-hiyouga 2025-01-15 11:06:19 +08:00
  • 9ef85f8fc4 [optim] clean apollo (#6645) hoshi-hiyouga 2025-01-15 01:42:50 +08:00
  • 763f9b9df0 [optim] add support to APOLLO (#6617) zhuHQ 2025-01-14 10:24:56 -06:00
  • 57043fb4e6 update readme of MiniCPM-o (#6642) Zhangchi Feng 2025-01-14 21:22:35 +08:00
  • 91433d639c lint (#6641) hoshi-hiyouga 2025-01-14 18:40:07 +08:00
  • 864ee06243 Support InternLM3 Dense 8B Model (#6640) Haian Huang(深度眸) 2025-01-14 18:07:27 +08:00
  • a52496cc09 Fix tokenizer max length (#6632) Xiaosu Zhu 2025-01-14 17:35:54 +08:00
  • ad119afc58 Support Inference of MiniCPM-V-2.6 and MiniCPM-o-2.6 (#6631) Zhangchi Feng 2025-01-14 17:34:58 +08:00
  • 8f73c75c16 [model] fix mllama any image (#6637) hoshi-hiyouga 2025-01-14 16:47:58 +08:00
  • 5e699458e5 pin vllm version to 0.6.5 (#6629) hoshi-hiyouga 2025-01-14 02:44:02 +08:00
  • 201a495154 Support new features of MiniCPM-V (#6626) Zhangchi Feng 2025-01-14 00:26:19 +08:00
  • d8cba9464f [inference] fix stop token for object detection (#6624) hoshi-hiyouga 2025-01-13 21:34:20 +08:00
  • 089c7d5e51 add nf4 qlora support on Ascend NPU (#6601) codingma 2025-01-13 19:43:36 +08:00
  • 15bba15725 Fix template name of MiniCPM-V (#6620) Zhangchi Feng 2025-01-13 16:46:48 +08:00
  • 0b47c2a293 Merge pull request #6598 from BUAADreamer/minicpmv hoshi-hiyouga 2025-01-13 15:24:02 +08:00
  • 313ce9a576 remove tests fzc8578 2025-01-13 15:08:35 +08:00
  • ee87d318b8 fix tests fzc8578 2025-01-13 15:01:39 +08:00
  • 4741eec2d1 fix style fzc8578 2025-01-13 14:19:38 +08:00
  • d2afe0c63c fix system prompt and tests fzc8578 2025-01-13 14:18:06 +08:00
  • bdded9d41a add some fzc8578 2025-01-11 15:03:20 +08:00
  • 8c79fe6a5a add cpm_o test fzc8578 2025-01-11 11:55:30 +08:00
  • 63bb2b7235 add cpm_o test fzc8578 2025-01-11 11:49:03 +08:00
  • e7f928adc4 fix format fzc8578 2025-01-11 01:27:40 +08:00
  • 62c12a133e add some fzc8578 2025-01-11 01:10:24 +08:00
  • 08e8499a98 adapt to new mllm_param fzc8578 2025-01-11 00:16:34 +08:00
  • d5b18ee4a6 Merge branch 'main' into minicpmv Zhangchi Feng 2025-01-11 00:01:36 +08:00
  • 93cc1f167b Merge pull request #6600 from hiyouga/hiyouga/refactor_mllm_param hoshi-hiyouga 2025-01-10 23:53:37 +08:00
  • c89d17ab63 refactor mllm param logic hiyouga 2025-01-10 15:41:54 +00:00
  • 9213e48fa2 add minicpmv2.6 fzc8578 2025-01-10 23:45:44 +08:00
  • 0fb50f9c88 add some fzc8578 2025-01-10 23:29:06 +08:00
  • bcbe37ff52 add some fzc8578 2025-01-10 21:25:32 +08:00
  • 994049380d fix some fzc8578 2025-01-10 20:55:52 +08:00
  • cc6a6f698f fix version fzc8578 2025-01-10 20:31:04 +08:00
  • 7138b43873 fix some fzc8578 2025-01-10 20:27:06 +08:00
  • aeb4f82ef2 tiny fix fzc8578 2025-01-10 20:15:39 +08:00
  • f51ac40f0a Merge branch 'main' into minicpmv Zhangchi Feng 2025-01-10 20:12:07 +08:00
  • 165fe8e219 add some fzc8578 2025-01-10 20:01:22 +08:00
  • 4243c618f0 Merge pull request #6597 from hiyouga/hiyouga/upd_wechat hoshi-hiyouga 2025-01-10 18:41:47 +08:00
  • 368d22f79a update wechat hiyouga 2025-01-10 10:40:25 +00:00
  • b3561ae552 Merge pull request #6588 from hiyouga/hiyouga/upd_issue_temp hoshi-hiyouga 2025-01-10 03:03:48 +08:00
  • b395540826 update issue template hiyouga 2025-01-09 18:56:49 +00:00
  • a1b5644889 Merge pull request #6585 from hiyouga/hiyouga/add_phi4 hoshi-hiyouga 2025-01-10 02:39:17 +08:00
  • b471def13d improve template, add phi4 model hiyouga 2025-01-09 18:27:20 +00:00
  • b777fed171 Merge pull request #6564 from stephen-nju/fix_ray hoshi-hiyouga 2025-01-08 18:14:18 +08:00
  • 618ceda6e9 Merge pull request #6565 from hiyouga/hiyouga/improve_log hoshi-hiyouga 2025-01-08 18:08:21 +08:00
  • 014a7ea042 fix –get ray args when args not a dict zhubin 2025-01-08 17:18:41 +08:00
  • da542fad18 imporve log hiyouga 2025-01-08 09:56:10 +00:00
  • 984b202f83 Merge pull request #6542 from erictang000/et/ray-integration hoshi-hiyouga 2025-01-08 11:46:03 +08:00
  • 0c1ad5f3fb fix llamaboard with ray hiyouga 2025-01-07 09:59:24 +00:00
  • b4174021d6 refactor ray integration, support save ckpt hiyouga 2025-01-07 08:54:41 +00:00
  • bba52e258e run style check Eric Tang 2025-01-06 23:55:56 +00:00