Edit model card

Mistral-7B-Instruct-v0.2-GGUF

New batch of quantized Mistral-7B-Instruct-v0.2 models using recent versions of llama.cpp.

GGUF

Model size

7.24B params

Architecture

llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Examples

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

Model tree for jpodivin/Mistral-7B-Instruct-v0.2-GGUF

Base model

Quantized

(85)

this model