THIS IS THE GGUF VERSION OF MISTED V2 7B. TO VIEW ORIGINAL MODEL CLICK THIS

Misted v2 7B

This is another version of misted-7b. This creation was designed to tackle coding, provide instructions, solve riddles, and fulfill a variety of purposes. It was developed using the slerp approach, which involved combining several mistral models with misted-7b.

Downloads last month
73
GGUF
Model size
7.24B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
Inference API (serverless) has been turned off for this model.