kroonen's picture
Update README.md
292c9e4
metadata
license: mit
datasets:
  - Intel/neuralchat_dataset_preprocessed
tags:
  - intel
  - neuralchat
  - gguf
  - llama
  - llama2
  - llamacpp

This is a quantized GGUF version of @intel neural-chat 3.1 7B quantized to 4_0 and 8_0 bits.

(link to the original model : https://huggingface.co/Intel/neural-chat-7b-v3-1/)