BlueMoonlight's picture
Upload README.md with huggingface_hub
ef99612 verified
metadata
library_name: vllm
language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - ru
  - zh
  - ja
license: apache-2.0
base_model: mistralai/Mistral-Nemo-Instruct-2407
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:
  - mistral-common
  - mlx
  - mlx-my-repo

BlueMoonlight/Mistral-Nemo-Instruct-2407-mlx-4Bit

The Model BlueMoonlight/Mistral-Nemo-Instruct-2407-mlx-4Bit was converted to MLX format from mistralai/Mistral-Nemo-Instruct-2407 using mlx-lm version 0.29.1.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("BlueMoonlight/Mistral-Nemo-Instruct-2407-mlx-4Bit")

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)