Sombressoul
/

GEITje-7B-GGUF

Model card Files Files and versions

GEITje-7B - GGUF

Model creator: Rijgersberg
Original model: GEITje-7B

This is a quantized (GGUF: Q8_0, Q6_K, Q5_K_M, Q4_K_M) version of GEITje-7B.

For more information about the model, see the original page.

Downloads last month: 25

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

Log In to add your hardware

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Sombressoul/GEITje-7B-GGUF

Base model

mistralai/Mistral-7B-v0.1

Finetuned

Rijgersberg/GEITje-7B

Quantized

(3)

this model