JefferyZhan/Qwen2.5-VL-7B-Instruct-Vision-R1

Partial fine-tune vs Qwen/Qwen2.5-VL-7B-Instruct. Partial change: 87% of the weights changed (attention, embeddings, mlp, norms), in 32 of 32 layers.

Tensors changed: Embeddings 1/2, Norms 57/122, MLP 279/280, Attention 324/324, lm_head 0/1

1 derivatives checked

• mradermacher/Qwen2.5-VL-7B-Instruct-Vision-R1-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse