JallyAI/Nomi-2
LoRA-style vs Qwen/Qwen3.5-4B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/5, MLP 96/199, Attention 32/324, Norms 0/209, other 0/1
3 derivatives checked
- mradermacher/Nomi-2-GGUF: Same weights, converted
- mradermacher/Nomi-2-i1-GGUF: Quantization
- JallyAI/Nomi-2-GGUF: Quantization