MaziyarPanahi/calme-2.3-llama3-70b
LoRA-style vs meta-llama/Meta-Llama-3-70B-Instruct. 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 80 of 80 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/161, MLP 240/240, Attention 320/320
3 derivatives checked
- MaziyarPanahi/calme-2.3-llama3-70b-GGUF: Quantization
- mradermacher/calme-2.3-llama3-70b-GGUF: Quantization
- mradermacher/calme-2.3-llama3-70b-i1-GGUF: Quantization