osmankoc/llama-2-7b-zoa
LoRA-style vs NousResearch/Llama-2-7b-chat-hf. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 64/160, lm_head 0/1
1 derivatives checked
- mradermacher/llama-2-7b-zoa-GGUF: Same weights, converted