mradermacher/wizardllama-7b-GGUF

Quantization vs axxd/wizardllama-7b. mradermacher/wizardllama-7b-GGUF is a GGUF quantization (Q8_0) of the same weights: 66 tensors match exactly and 225 within quantization error.

Tensors changed: MLP 0/96, Norms 0/65, Attention 0/128, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse