mpasila/Llama-3-MetaRP-V2-8B
LoRA-style vs Undi95/Meta-Llama-3-8B-Instruct-hf. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, up_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 96/96, Attention 0/128, lm_head 0/1
2 derivatives checked
- mradermacher/Llama-3-MetaRP-V2-8B-i1-GGUF: Quantization
- mradermacher/Llama-3-MetaRP-V2-8B-GGUF: Same weights, converted