Lunzima/NQLSG-Qwen2-VL-2B-v2-Base

Full fine-tune vs Qwen/Qwen2-VL-2B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 2/2, Norms 187/187, MLP 216/216, Attention 324/324

1 derivatives checked

• mradermacher/NQLSG-Qwen2-VL-2B-v2-Base-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse