README.md

metadata

language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - zh
  - ja
  - ru
  - ko
license: apache-2.0
library_name: vllm
base_model: mlx-community/Mistral-Small-24B-Instruct-2501-4bit
extra_gated_description: >-
  If you want to learn more about how we process your personal data, please read
  our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
tags:
  - mlx
  - mlx
  - mlx-my-repo

CuckmeisterFuller/Mistral-Small-24B-Instruct-2501-4bit-Q2-mlx

The Model CuckmeisterFuller/Mistral-Small-24B-Instruct-2501-4bit-Q2-mlx was converted to MLX format from mlx-community/Mistral-Small-24B-Instruct-2501-4bit using mlx-lm version 0.20.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("CuckmeisterFuller/Mistral-Small-24B-Instruct-2501-4bit-Q2-mlx")

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)