tdot604/Hazy-Llama-70b
LoRA-style vs Sao10K/L3-70B-Euryale-v2.1. 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
2 derivatives checked
- mradermacher/Hazy-Llama-70b-i1-GGUF: Quantization
- mradermacher/Hazy-Llama-70b-GGUF: Quantization