423A35C7

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-01-07 22:50:35 +08:00

5cfd804b59 [refactor] rename lfm template to lfm2 and add LFM 2.5 to README (#9731)

4c1eb922e2 [misc] fix parser (#9730)

958fb523a2 [model] support LiquidAI's LFM2.5-VL vision-language model (#9729)

Compare 3 commits »

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-01-07 14:40:36 +08:00

b4e051bea4 [model] support for LiquidAI's LFM2.5 (Liquid Foundation Models) (#9726)

d43e1007e8 [ci] improve cuda ci cache (#9725)

f89d9367e5 [assets] update README.md (#9724)

Compare 3 commits »

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-01-07 06:30:36 +08:00

d22de0d4bf [v1] add renderer ut (#9722)

ea0b4e2466 [v1] add cli sampler (#9721)

e944dc442c [feature] add support for EAFT loss (#9720)

Compare 3 commits »

423A35C7 synced and deleted reference refs/tags/hiyouga/chat at 423A35C7/LLaMA-Factory from mirror 2026-01-07 06:30:36 +08:00

423A35C7 synced new reference hiyouga/chat to 423A35C7/LLaMA-Factory from mirror 2026-01-06 22:20:35 +08:00

423A35C7 synced commits to hiyouga/chat at 423A35C7/LLaMA-Factory from mirror 2026-01-06 22:20:35 +08:00

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-01-05 13:40:34 +08:00

68119e5522 [misc] Add a PyTorch version warning for Conv3D. (#9715)

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-01-04 21:20:40 +08:00

f60a6e3d01 [v1] add init plugin (#9716)

81b8a50aa5 [deps] Update pyproject.toml and requirements (#9714)

8600530002 [misc] lint (#9710)

9ae62c6fc0 [model] support Youtu-LLM-2B (#9707)

Compare 4 commits »

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-01-04 13:10:35 +08:00

0087bc253b [misc] Compatible with an empty architectures field in config.json (#9709)

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-01-01 11:40:35 +08:00

355d5c5e5a [fix] fp8: add Transformer Engine backend support (#9705)

423A35C7 synced new reference refs/tags/v0.9.4 to 423A35C7/LLaMA-Factory from mirror 2026-01-01 03:30:35 +08:00

423A35C7 synced commits to refs/tags/v0.9.4 at 423A35C7/LLaMA-Factory from mirror 2026-01-01 03:30:35 +08:00

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-01-01 03:30:35 +08:00

6fe6bd290b [misc] set dev version (#9703)

95ac3f2373 [release] Bye 2025 (#9702)

000526908a [core deps] upgrade TRL to be between 0.18 and 0.24 (#9617)

Compare 3 commits »

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2025-12-31 19:20:36 +08:00

c8d7e85b3e [fix] Fix prediction metrics in scripts/vllm_infer.py to match Transformers (#9701)

16735b9e35 [v1] Refactor kernel plugin (#9669)

Compare 2 commits »

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2025-12-31 03:00:35 +08:00

4e1d69579a [data] add DLR-Web dataset for supervised fine-tuning (#9696)

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2025-12-30 02:30:35 +08:00

1857fbdd6b [ci] add cuda workflow (#9682)

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2025-12-29 18:20:35 +08:00

bb1ba31005 [misc] lint mca code (#9692)

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2025-12-29 02:00:36 +08:00

e97d0474fb [ci] Fix NPU device condition in docker workflow (#9688)

3f0c3dc84d [assets] fix installation (#9687)

c107cc22d0 [model] support MiniMax-M1&M2 series (#9680)

Compare 3 commits »

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2025-12-28 09:40:34 +08:00

7ef1fba34a [version] fix gradio (#9685)

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2025-12-27 09:10:35 +08:00

eceec8ab69 [deps] goodbye python 3.9 (#9677)

b44f651e09 [ci] fix docker (#9678)

55590f5ece [misc] fix ci with uv (#9676)

Compare 3 commits »