metadata
language:
- en
library_name: mlx
license: apache-2.0
tags:
- unsloth
- transformers
- mistral
- mistral-7b
- mistral-instruct
- instruct
- mlx
pipeline_tag: text-generation
base_model: unsloth/mistral-7b-instruct-v0.3
ilopezluna/something
This model ilopezluna/something was converted to MLX format from unsloth/mistral-7b-instruct-v0.3 using mlx-lm version 0.25.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("ilopezluna/something")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)