mradermacher/ANIMA-Phi-Neptune-Mistral-10.7B-GGUF

Quantization vs Joseph717171/ANIMA-Phi-Neptune-Mistral-10.7B. mradermacher/ANIMA-Phi-Neptune-Mistral-10.7B-GGUF is a GGUF quantization (Q8_0) of the same weights: 97 tensors match exactly and 338 within quantization error.

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

On the Hub · Downloads on Model Pulse