lahey's picture
e0266c8f8099b621fd9599ea1fca647df816a9034b07499423d332fef29fe58b
b20617e verified
|
raw
history blame
691 Bytes
metadata
license: apache-2.0
pipeline_tag: text-generation
tags:
  - finetuned
  - mlx
inference: true
widget:
  - messages:
      - role: user
        content: What is your favorite condiment?

lahey/My-mistral-7b-instruct

The Model lahey/My-mistral-7b-instruct was converted to MLX format from mistralai/Mistral-7B-Instruct-v0.2 using mlx-lm version 0.15.0.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("lahey/My-mistral-7b-instruct")
response = generate(model, tokenizer, prompt="hello", verbose=True)