tanhuajie2001/Robo-Dopamine-GRM-2.0-4B-Preview

Full fine-tune vs Qwen/Qwen3-VL-4B-Instruct. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 4/4, Norms 217/249, MLP 219/220, Attention 240/240

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

On the Hub · Downloads on Model Pulse