Commit Graph

  • 151ef48b40 [data] fix function formatter (#7201) ZhangChuanhui 2025-03-07 15:17:23 +08:00
  • a255c3a476 [misc] fix cli (#7204) hoshi-hiyouga 2025-03-07 15:01:18 +08:00
  • f4ec4fa6ad [script] fix vllm version (#7193) hoshi-hiyouga 2025-03-06 17:14:17 +08:00
  • 2635794727 [webui] support escape html (#7190) hoshi-hiyouga 2025-03-06 16:52:21 +08:00
  • d2f845d70d [deps] upgrade vllm (#7183) hoshi-hiyouga 2025-03-06 15:25:08 +08:00
  • bb8aba5abf [data] fix mm template (#7181) hoshi-hiyouga 2025-03-06 15:18:32 +08:00
  • 9f16c50155 [model] add QwQ 32b (#7179) hoshi-hiyouga 2025-03-06 11:58:36 +08:00
  • 25bb9f5ad9 [trainer] fix swanlab callback (#7176) Ze-Yi LIN 2025-03-06 00:33:37 +08:00
  • 7b985f55db [trainer] update config (#7174) hoshi-hiyouga 2025-03-05 23:32:54 +08:00
  • fd0357a26d [data] fix qwen2audio plugin (#7166) sirui.li 2025-03-05 18:03:36 +08:00
  • 31f9daa362 [data] use bicubic resampler (#7143) hoshi-hiyouga 2025-03-04 00:17:06 +08:00
  • 15ea576246 [webui] fix webui (#7142) hoshi-hiyouga 2025-03-04 00:01:49 +08:00
  • 19a6916d80 [data] bailing template (#7117) rabbit 2025-03-03 15:33:22 +08:00
  • 585c475f71 [inference] fix hf_engine (#7120) hoshi-hiyouga 2025-03-01 05:22:49 +08:00
  • e62dae37fe [assets] update wechat (#7106) hoshi-hiyouga 2025-02-28 12:01:04 +08:00
  • 11672f760d [webui] display swanlab exp link (#7089) Ze-Yi LIN 2025-02-27 19:40:54 +08:00
  • b9f84900ee [npu] update cann base image and torch 2.4 (#7061) leo-pony 2025-02-25 23:32:01 +08:00
  • 5f65558088 [misc] fix project toml (#7067) hoshi-hiyouga 2025-02-25 23:22:48 +08:00
  • 0f54a78144 [script] add seed args (#7058) JieShen 2025-02-25 19:44:57 +08:00
  • 2986bef530 [model] add paligemma2-mix series (#7060) Kingsley 2025-02-25 18:51:16 +08:00
  • 065f7fb5da [data] fix mllama (#7053) hoshi-hiyouga 2025-02-24 22:05:38 +08:00
  • c1d5073bd3 [model] add models (#7054) hoshi-hiyouga 2025-02-24 22:05:13 +08:00
  • ee46011b34 [assets] update readme (#7051) hoshi-hiyouga 2025-02-24 20:45:06 +08:00
  • d55f420206 [assets] update wechat (#7019) hoshi-hiyouga 2025-02-20 20:32:33 +08:00
  • fcf75633a0 [data] fix MiniCPMV plugin (#6998) Zhangchi Feng 2025-02-19 19:36:04 +08:00
  • e77ced045d [webui] update css (#6985) hoshi-hiyouga 2025-02-18 18:27:57 +08:00
  • 331f53381f [data] add r1 distill dataset (#6983) hoshi-hiyouga 2025-02-18 17:25:09 +08:00
  • 1d675a287d [version] support transformers 449 (#6982) hoshi-hiyouga 2025-02-18 17:05:40 +08:00
  • be33ef67fb [misc] fix script (#6977) hoshi-hiyouga 2025-02-18 17:00:46 +08:00
  • f5cd17881e [data] update vlm args (#6976) hoshi-hiyouga 2025-02-18 02:12:51 +08:00
  • c09b648934 [data] add min resolution option (#6975) hoshi-hiyouga 2025-02-18 01:40:46 +08:00
  • f2fd9d1b25 [data] fix predict dataset (#6972) hoshi-hiyouga 2025-02-17 20:29:40 +08:00
  • 167342af8a [data] fix minicpmo template (#6946) Zhangchi Feng 2025-02-15 00:37:41 +08:00
  • 76f9bd1820 [ray] specify ray storage path (#6920) Eric Tang 2025-02-14 05:55:41 -08:00
  • a893505924 [misc] fix lora regex (#6944) hoshi-hiyouga 2025-02-14 21:38:43 +08:00
  • ed25e051a9 [misc] fix grad ckpt (#6931) hoshi-hiyouga 2025-02-13 23:27:51 +08:00
  • 5e5fc337f9 [model] add liger kernel to qwen2_5 vl (#6930) hoshi-hiyouga 2025-02-13 23:05:54 +08:00
  • 58e9ca8aa0 [trainer] fix gen_kwarg to eval during training (#5451) Billy Cao 2025-02-13 02:35:06 +08:00
  • a4c4b8496f [data] evaluate on each dataset (#5522) SrWYG 2025-02-13 02:19:03 +08:00
  • 38c9641777 [data] improve error handling (#6128) Noah 2025-02-13 01:39:41 +08:00
  • 8b8fdb3a85 [misc] update readme (#6918) hoshi-hiyouga 2025-02-13 01:01:41 +08:00
  • 290057069e [misc] update readme (#6917) hoshi-hiyouga 2025-02-13 00:58:10 +08:00
  • 46203856fc [breaking change] refactor data pipeline (#6901) hoshi-hiyouga 2025-02-13 00:39:20 +08:00
  • 80b89978d9 [misc] support for launching LLaMA-Factory with uv run (#6907) Eric Tang 2025-02-12 08:38:44 -08:00
  • 5a221d91f9 [example] fix path to ray example (#6906) Eric Tang 2025-02-12 08:29:32 -08:00
  • 3a3f4072e5 [misc] fix grad ckpt func (#6916) hoshi-hiyouga 2025-02-13 00:17:18 +08:00
  • 0c0cdc26bc [trainer] fix llama3.2 vision kto train (#6904) marko1616 2025-02-12 19:09:14 +08:00
  • 2581cc844b [data] feat: auto template (#6905) hoshi-hiyouga 2025-02-12 00:22:53 +08:00
  • d58fcd094e [misc] update readme (#6903) hoshi-hiyouga 2025-02-11 22:51:26 +08:00
  • 86063e27ea [data] fix ollama template (#6902) hoshi-hiyouga 2025-02-11 22:43:09 +08:00
  • 88eafd865b [misc] support export ollama modelfile (#6899) hoshi-hiyouga 2025-02-11 19:52:25 +08:00
  • 3f7bd98bfa [data] refactor template (#6896) hoshi-hiyouga 2025-02-11 17:59:25 +08:00
  • b72c4bd118 support ollama modelfile export (#4686) codingma 2025-02-11 17:52:24 +08:00
  • 808ff89a2d [data] refactor mm plugin (#6895) hoshi-hiyouga 2025-02-11 16:34:49 +08:00
  • 6d7f1299bd [data] fix qwen_2_5_vl video processing (#6868) HJ 2025-02-11 16:14:50 +08:00
  • 0420a608ca [assets] update wechat (#6892) hoshi-hiyouga 2025-02-11 13:56:26 +08:00
  • 2047eab723 [da'ta] fix minicpmv plugin (#6890) Zhangchi Feng 2025-02-11 13:30:44 +08:00
  • e11b40c344 [data] fix: sharegpt converter (#6879) HJ 2025-02-10 21:59:12 +08:00
  • b869506a57 [data] fix mllama collator (#6874) hoshi-hiyouga 2025-02-09 22:42:25 +08:00
  • 72d5b06b08 [test] align test cases (#6865) hoshi-hiyouga 2025-02-09 01:03:49 +08:00
  • 94726bdc8d [dataset] add openthought (#6866) hoshi-hiyouga 2025-02-09 00:53:01 +08:00
  • 4d1791e905 [deps] upgrade vllm (#6857) hoshi-hiyouga 2025-02-08 15:02:28 +08:00
  • 528e06ccaa fix qwen2vl plugin (#6855) hoshi-hiyouga 2025-02-08 10:59:10 +08:00
  • fec641ec82 [misc] allow extra args (#6831) hoshi-hiyouga 2025-02-06 12:38:08 +08:00
  • 8f401e37f8 [model] support audio (#6701) Zhangchi Feng 2025-02-05 04:59:09 +08:00
  • 9feb78e7b4 [data] allow thought in function call (#6797) Yueqi Song 2025-02-05 02:26:23 +08:00
  • c2022431aa [misc] update license year & fix llama pro (#6814) hoshi-hiyouga 2025-02-05 01:53:33 +08:00
  • 0817c24c04 [data] fix qwen tool template (#6796) Yueqi Song 2025-02-05 00:02:00 +08:00
  • cfb926fb84 [data] fix minicpmv plugin (#6801) Zhangchi Feng 2025-02-04 21:20:15 +08:00
  • 34746d6151 [readme] update flash attention installation instruction on win platform (#6788) neavo 2025-02-01 12:43:29 +08:00
  • 5bb447b118 [misc] update workflows (#6787) hoshi-hiyouga 2025-02-01 04:54:42 +08:00
  • a28261a866 [model] add mistral small models (#6786) hoshi-hiyouga 2025-02-01 04:31:38 +08:00
  • 800de98dc8 [model] add qwen2.5 vl models (#6779) hoshi-hiyouga 2025-01-31 03:00:29 +08:00
  • 222423bcef [breaking] support transformers 4.48 (#6628) hoshi-hiyouga 2025-01-31 01:36:33 +08:00
  • e71737351f [webui] improve webui & reasoning mode (#6778) hoshi-hiyouga 2025-01-31 00:09:21 +08:00
  • 4f298894da [model] add deepseek-R1 & show think process (#6767) qvlehao 2025-01-29 12:16:26 +08:00
  • a8fae3869d fix: avoid redundant normalization in DPO's SFT loss calculation (#6722) yinpu 2025-01-21 13:38:02 +08:00
  • db9b977e4f [webui] support ja (#6698) engchina 2025-01-20 19:46:38 +08:00
  • 87d685b59f [model] support yarn (#6693) hoshi-hiyouga 2025-01-18 13:56:09 +08:00
  • e4046bdd1f [assets] update wechat (#6692) hoshi-hiyouga 2025-01-18 12:35:03 +08:00
  • 5baa3add8c [misc] update mm plugin (#6691) hoshi-hiyouga 2025-01-17 23:04:26 +08:00
  • 332f637592 disable valset by default (#6690) hoshi-hiyouga 2025-01-17 21:09:30 +08:00
  • 31daa6570b [webui] upgrade to gradio 5 (#6688) hoshi-hiyouga 2025-01-17 20:15:42 +08:00
  • 33525a34b6 fix qwen2 moe (#6684) hoshi-hiyouga 2025-01-17 13:46:09 +08:00
  • 3607caa2ad [data] Fix minicpmv/o dpo training (#6657) Zhangchi Feng 2025-01-15 17:30:37 +08:00
  • 0fc2e19279 Update val_size english description (#6653) steveepreston 2025-01-15 11:30:20 +03:30
  • ef994600db update readme (#6648) hoshi-hiyouga 2025-01-15 11:06:19 +08:00
  • 7638f1070e [optim] clean apollo (#6645) hoshi-hiyouga 2025-01-15 01:42:50 +08:00
  • c2120432db [optim] add support to APOLLO (#6617) zhuHQ 2025-01-14 10:24:56 -06:00
  • 66184762e8 update readme of MiniCPM-o (#6642) Zhangchi Feng 2025-01-14 21:22:35 +08:00
  • 41a9e231cb lint (#6641) hoshi-hiyouga 2025-01-14 18:40:07 +08:00
  • 1bb06e06df Support InternLM3 Dense 8B Model (#6640) Haian Huang(深度眸) 2025-01-14 18:07:27 +08:00
  • 381f7120e6 Fix tokenizer max length (#6632) Xiaosu Zhu 2025-01-14 17:35:54 +08:00
  • f7857c83e1 Support Inference of MiniCPM-V-2.6 and MiniCPM-o-2.6 (#6631) Zhangchi Feng 2025-01-14 17:34:58 +08:00
  • d0da6f40b0 [model] fix mllama any image (#6637) hoshi-hiyouga 2025-01-14 16:47:58 +08:00
  • 28d145a066 pin vllm version to 0.6.5 (#6629) hoshi-hiyouga 2025-01-14 02:44:02 +08:00
  • ae32c148d1 Support new features of MiniCPM-V (#6626) Zhangchi Feng 2025-01-14 00:26:19 +08:00
  • 2a05941b14 [inference] fix stop token for object detection (#6624) hoshi-hiyouga 2025-01-13 21:34:20 +08:00
  • 11c38b9173 add nf4 qlora support on Ascend NPU (#6601) codingma 2025-01-13 19:43:36 +08:00
  • 73c1c15b62 Fix template name of MiniCPM-V (#6620) Zhangchi Feng 2025-01-13 16:46:48 +08:00