robometer/Robometer-4B

Partial fine-tune vs Qwen/Qwen3-VL-4B-Instruct. Partial change: 90% of the weights changed (attention, mlp, norms), in 36 of 36 layers.

Tensors changed: Norms 91/249, MLP 108/220, Attention 144/240, Embeddings 0/3

1 derivatives checked

• lerobot/Robometer-4B: Same weights, repacked

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

On the Hub · Downloads on Model Pulse