mlx-community/Mistral-7B-Instruct-v0.3

The Model mlx-community/Mistral-7B-Instruct-v0.3 was converted to MLX format from mistralai/Mistral-7B-Instruct-v0.3 using mlx-lm version 0.16.0.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Mistral-7B-Instruct-v0.3")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
98
Safetensors
Model size
7.25B params
Tensor type
FP16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mlx-community/Mistral-7B-Instruct-v0.3

Finetunes
1 model

Collection including mlx-community/Mistral-7B-Instruct-v0.3