smpanaro/Llama-2-7b-NuGPTQ
LoRA-style (fewer layers) vs meta-llama/Llama-2-7b-hf. meta-llama/Llama-2-7b-hf matches part of smpanaro/Llama-2-7b-NuGPTQ (291 of its 515 tensors; the rest of smpanaro/Llama-2-7b-NuGPTQ has no counterpart). On the shared part: 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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 0/1