drissea-ai/drissy-qwen3.5-2b
Partial fine-tune vs Qwen/Qwen3.5-2B-Base. Partial change: 87% of the weights changed (attention, embeddings, mlp, norms, other), in 24 of 24 layers.
Tensors changed: Attention 146/268, Norms 87/183, Embeddings 3/5, MLP 79/175, other 1/1
2 derivatives checked
- mradermacher/drissy-qwen3.5-2b-i1-GGUF: Quantization
- mradermacher/drissy-qwen3.5-2b-GGUF: Same weights, converted