lewiswatson/Frame2KG-Qwen3.5-4b-JSON

Partial fine-tune vs Qwen/Qwen3.5-4B. lewiswatson/Frame2KG-Qwen3.5-4b-JSON is a GGUF (F16) of different weights. Partial change: 80% of the weights changed (attention, mlp, norms), in 32 of 32 layers.

Tensors changed: Embeddings 0/1, MLP 96/96, Norms 64/81, Attention 32/32

On the Hub · Downloads on Model Pulse