Edit model card

mathstral-7B-v0.1-GGUF

Original Model

mistralai/mathstral-7B-v0.1

Run with Gaianet

Prompt template:

prompt template: mistral-instruct

Context size:

chat_ctx_size: 32000

Run with GaiaNet:

Quantized with llama.cpp b3389

Downloads last month
187
GGUF
Model size
7.25B 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 gaianet/mathstral-7B-v0.1-GGUF

Quantized
(20)
this model