wkinglin/HalluScope-4B

Full fine-tune vs Qwen/Qwen3-VL-4B-Instruct. Fine-tune: 91% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 3/4, Norms 170/249, MLP 212/220, Attention 240/240

1 derivatives checked

• mradermacher/HalluScope-4B-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse