bestler/Code-Summary-Llama-3.2-3B-Instruct
LoRA-style vs mlx-community/Llama-3.2-3B-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 56/112
1 derivatives checked
- mradermacher/Code-Summary-Llama-3.2-3B-Instruct-GGUF: Same weights, converted