Initial Model: cognitivecomputations/dolphin-2.8-experiment26-7b
Model Status: First epoch checkpoint

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:

GGUF

Model size

7.24B params

Architecture

llama

4-bit

5-bit

6-bit

Inference API

Unable to determine this model's library. Check the docs .