---
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:

- Sao10K/Stheno-L2-13B: https://huggingface.co/Sao10K/Stheno-L2-13B
- FantasiaFoundry/GGUF-Quantization-Script: https://huggingface.co/FantasiaFoundry/GGUF-Quantization-Script