423A35C7

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-07-11 03:25:28 +08:00

b61140db3e [v1] replace custom template system with apply_chat_template (#10598)

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-07-09 02:25:28 +08:00

ea31c43d80 [v1] improve getting started guide with comprehensive content (#10626)

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-07-07 17:45:26 +08:00

76a0391ddd [misc] fix ray initialization comment typo (#10628)

445163ab5e [misc] fix typos in comments and help text (#10633)

d58ec6a0bc [deps] exclude broken transformers release (#10634)

5987a8dd68 [webui] add seed controls for reproducibility (#10629)

Compare 4 commits »

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-07-03 15:45:28 +08:00

a61cfa692a [readme] Revise bitsandbytes installation instructions in README (#10621)

7a83d28ce3 [readme] Revise bitsandbytes installation instructions (#10622)

Compare 2 commits »

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-07-02 15:15:27 +08:00

c8a082e0e3 [fix] Fixes Qwen3-VL prompt expansion for multiple videos (#10518)

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-06-30 22:25:26 +08:00

a48af5cc69 [data] clarify _nothink suffix warning for reasoning-only models (#10613)

c383c0d067 [model] add Qwen-AgentWorld-35B-A3B support (#10615)

50ff45176a [v1] set flash_attn to flash_attention_2 for ulysses CP example (#10616)

Compare 3 commits »

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-06-27 20:58:56 +08:00

9c0b4b3835 [v1][feature] add dpo trainer (#10544)

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-06-26 00:58:54 +08:00

b7615dbdc9 [v1] Fix device mesh, fix lora for reward model and fix sp (#10555)

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-06-25 00:28:54 +08:00

666ee0ca78 [fix] redundant transformers check (#10602)

aca54c7f17 [model] add Hy-MT2-1.8B/7B support (#10605)

Compare 2 commits »

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-06-24 16:18:55 +08:00

48aa9ef084 [docs] update supported models list for MiniCPM 4/5 (#10603)

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-06-23 23:58:55 +08:00

c928c1cb21 [assets] update llamafactory sft skill guidance (#10600)

423A35C7 synced commits to main at 423A35C7/pytorch3d from mirror 2026-06-23 23:48:54 +08:00

c8fcd83ff9 Fix CQS signal facebook-unused-include-check in fbcode/vision/fair [A] [A] [A]

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-06-22 23:28:57 +08:00

c35b7d7f55 [assets] add llamafactory sft skills (#10597)

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-06-22 15:19:00 +08:00

802bcfe969 [feat] support HyperParallel Context Parallel feature (#10559)

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-06-17 20:58:54 +08:00

8792f06161 [webui] Fix WebUI training hang from subprocess log pipe (#10584)

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-06-16 20:28:54 +08:00

8669a22e9c [fix] fix liger kernel patch for npu (#10583)

897a44386c [docs] add DataFlow and DataFlex blog tutorials (#10582)

Compare 2 commits »

423A35C7 synced commits to main at 423A35C7/LLaMA-Factory from mirror 2026-06-15 19:58:54 +08:00

7a1e9630f2 [fix] update ascend doc link (#10572)

423A35C7 synced commits to main at 423A35C7/pytorch3d from mirror 2026-06-13 18:48:54 +08:00

7f8a8a142f Image.ANTIALIAS -> Image.Resampling.LANCZOS

423A35C7 synced commits to main at 423A35C7/pytorch3d from mirror 2026-06-11 17:48:53 +08:00

f137c87cf9 Suppress type errors for Pyre upgrade

423A35C7 synced commits to main at 423A35C7/pytorch3d from mirror 2026-06-11 09:38:53 +08:00

d34e87ce52 validate input and edges dtype in GatherScatter python wrapper