dnotitia/DNA-VL-STEER-2B

Partial fine-tune vs Qwen/Qwen3-VL-Embedding-2B. Partial change: 9% of the weights changed (attention, mlp, norms), in 4 of 28 layers.

Tensors changed: Embeddings 0/4, Norms 14/217, MLP 12/196, Attention 16/208

1 derivatives checked

• mradermacher/DNA-VL-STEER-2B-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse