mradermacher/Hermes-2-Pro-Mistral-10.7B-GGUF

Quantization vs Joseph717171/Hermes-2-Pro-Mistral-10.7B. mradermacher/Hermes-2-Pro-Mistral-10.7B-GGUF is a GGUF quantization (Q8_0) of the same weights: 98 tensors match exactly and 337 within quantization error.

Tensors changed: Norms 0/97, MLP 0/144, Attention 0/192, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse