StarVLA/Qwen3-VL-4B-Instruct-Action
Same weights, repacked vs Qwen/Qwen3-VL-4B-Instruct. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Norms 0/249, MLP 0/220, Attention 0/240, Embeddings 0/3
Same weights, repacked vs Qwen/Qwen3-VL-4B-Instruct. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Norms 0/249, MLP 0/220, Attention 0/240, Embeddings 0/3