weihongliang/RC-Qwen2VL-2b

Partial fine-tune vs Qwen/Qwen2-VL-2B. Partial change: 71% of the weights changed (attention, embeddings, mlp, norms), in 28 of 32 layers.

Tensors changed: Embeddings 1/2, Norms 57/187, MLP 88/216, Attention 196/324

2 derivatives checked

• mradermacher/RC-Qwen2VL-2b-i1-GGUF: Quantization (fewer layers)
• mradermacher/RC-Qwen2VL-2b-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse