abdukuzi45/qwen3.5-amharic-4b-thinking-uncensored

Partial fine-tune vs Qwen/Qwen3.5-4B. Partial change: 27% of the weights changed (attention, mlp, norms), in 32 of 32 layers.

Tensors changed: Embeddings 0/2, MLP 32/99, Attention 42/228, Norms 27/111, other 0/1

2 derivatives checked

• mradermacher/qwen3.5-amharic-4b-thinking-GGUF: Same weights, converted
• abdukuzi45/Qwen3.5-amharic-4b-thinking-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse