ProCreations/grug-3b
LoRA-style vs Nanbeige/Nanbeige4.2-3B. 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 22 of 22 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/45, MLP 66/66, Attention 88/88
5 derivatives checked
- bartowski/ProCreations_grug-3b-GGUF: Same weights, converted
- mradermacher/grug-3b-i1-GGUF: Quantization
- ProCreations/grug-3b-gguf: Same weights, converted
- mradermacher/grug-3b-GGUF: Same weights, converted
- ProCreations/grug-3b-qat-q4-gguf: LoRA-style