unsloth/Qwen2.5-VL-7B-Instruct

Same weights, repacked vs Qwen/Qwen2.5-VL-7B-Instruct. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/2, Norms 0/122, MLP 0/280, Attention 0/324, lm_head 0/1

3 derivatives checked

• REEA-GLOBAL/Qwen2.5-VL-7B-Instruct-ft-20250814163916929: LoRA-style
• prakcoin/QwENDEAVR2.5-VL-NoCNN: LoRA-style
• prakcoin/QwENDEAVR2.5-VL-Base: LoRA-style

36 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse