kody0525/KOpen-platypus-llama-2-ko-7b
LoRA-style vs beomi/llama-2-ko-7b. 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
1 derivatives checked
- mradermacher/KOpen-platypus-llama-2-ko-7b-GGUF: Same weights, converted