sensenova/SenseNova-SI-1.2-InternVL3-8B

Partial fine-tune vs OpenGVLab/InternVL3-8B. Partial change: 89% of the weights changed (attention, lm_head, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/5, Norms 56/153, MLP 90/186, Attention 196/292, other 0/48, lm_head 1/1

2 derivatives checked

• mradermacher/SenseNova-SI-1.2-InternVL3-8B-i1-GGUF: Quantization (fewer layers)
• mradermacher/SenseNova-SI-1.2-InternVL3-8B-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse