Novaciano/Hug_Of_Bear-3.2-1B
LoRA-style vs Novaciano/Eminence_Of_Pervertions-3.2-1B. 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 16 of 16 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/33, MLP 37/48, Attention 40/64
2 derivatives checked
- mradermacher/Hug_Of_Bear-3.2-1B-i1-GGUF: Quantization
- mradermacher/Hug_Of_Bear-3.2-1B-GGUF: Same weights, converted