internlm/CapRL-InternVL3.5-8B

Full fine-tune vs OpenGVLab/InternVL3_5-8B. Fine-tune: 92% of the weights changed, across 36 of 36 layers.

Tensors changed: MLP 108/108, Norms 105/145, Attention 144/144, lm_head 1/1, Embeddings 0/1

1 derivatives checked

• Jobaar/CapRL-InternVL3.5-8B-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse