metadata
base_model: mlx-community/Mistral-7B-Instruct-v0.2-4bit
license: apache-2.0
pipeline_tag: text-generation
tags:
- finetuned
- mlx
- mlx
inference: true
widget:
- messages:
- role: user
content: What is your favorite condiment?
AravD/Mistral-7B-Instruct-PaulAI
The Model AravD/Mistral-7B-Instruct-PaulAI was converted to MLX format from mlx-community/Mistral-7B-Instruct-v0.2-4bit using mlx-lm version 0.19.0.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("AravD/Mistral-7B-Instruct-PaulAI")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)