drwlf/Medra4b-65424
LoRA-style vs google/gemma-3-4b-it. 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 34 of 34 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/316, MLP 102/210, Attention 136/352, other 0/1, Embeddings 0/3
2 derivatives checked
- mradermacher/Medra4b-65424-i1-GGUF: Quantization (fewer layers)
- mradermacher/Medra4b-65424-GGUF: Same weights, converted (fewer layers)