Vebbern/Qwen2.5-VL-3B-R2R-low-level

Partial fine-tune vs Qwen/Qwen2.5-VL-3B-Instruct. Partial change: 74% of the weights changed (attention, mlp, norms), in 36 of 36 layers.

Tensors changed: Embeddings 0/2, Norms 70/138, MLP 108/304, Attention 244/380

2 derivatives checked

• mradermacher/Qwen2.5-VL-3B-R2R-low-level-i1-GGUF: Quantization (fewer layers)
• mradermacher/Qwen2.5-VL-3B-R2R-low-level-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse