---
license: apache-2.0
---
Initial Model:  cognitivecomputations/dolphin-2.8-experiment26-7b  
Model Status: <b>First epoch checkpoint</b>

Original Author: Eric Hartford

Overview

This repository hosts GGUF format model files designed for  cognitivecomputations/dolphin-2.8-experiment26-7b model.

GGUF can be used in:

Llama.cpp as of December 13th  
Llama.cui  
KoboldCpp 1.52 +  
LM Studio 0.2.9 +  
llama-cpp-python 0.2.23 +  
node-llama  

Test of Q5_K_S Model with Llama.cui:

![image/png](https://cdn-uploads.huggingface.co/production/uploads/648bed1b18588b6e5dbc080e/NWkWc3NZ1wogHien_TC6Z.png)