Files
hao-ai-lab-FastVideo/fastvideo/models
Will LinandClaude Fable 5 ead828a726 [bugfix]: make custom qwen2.5-vl encoder compatible with transformers 5.x
transformers>=5 stops forwarding text-model attributes from the composite
Qwen2_5_VLConfig, drops the 'default' ROPE_INIT_FUNCTIONS entry, and requires
flash-attn functions to be preloaded before _flash_attention_forward. Flatten
text_config at model entry, replicate the 4.x default rope init, and preload
flash-attn (falling back to SDPA). Fixes Kandinsky5 and Cosmos 2.5 encoder
loading under the transformers>=4.57.3 pin.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-07 14:35:48 -07:00
..
2026-07-07 14:35:48 -07:00
2025-07-24 22:43:12 -07:00
2025-12-21 00:57:52 -06:00
2025-07-24 22:43:12 -07:00