SolidSnacke's picture
Update README.md
a7b3b62 verified
metadata
license: llama2
language:
  - en
library_name: transformers
pipeline_tag: text-generation
tags:
  - llama
  - text-generation-inference

Want to make a couple models: ( • ̀ω•́ )✧

Downloading the original model, quantizing the GGUF-F16 model, creating imatrix.dat, quantizing the required models and then uploading them to the repository. In total, 4 and a half hours were spent: 💀

(It’s a pity I don’t have normal hardware for quantization)

Link to original model and script: