metadata
license: apache-2.0
language:
- en
- ru
base_model: Vikhrmodels/Vistral-24B-Instruct
library_name: mlx
datasets:
- Vikhrmodels/GrandMaster2
tags:
- mlx
pipeline_tag: text-generation
Vikhrmodels/Vistral-24B-Instruct-MLX_4bit
This model Vikhrmodels/Vistral-24B-Instruct-MLX_4bit was converted to MLX format from Vikhrmodels/Vistral-24B-Instruct using mlx-lm version 0.26.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Vikhrmodels/Vistral-24B-Instruct-MLX_4bit")
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)