prince-canuma's picture
Add files using upload-large-folder tool
e39e0ca verified
|
raw
history blame
1.15 kB
metadata
library_name: mlx
inference: false
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
license: other
pipeline_tag: text-generation
base_model: mistralai/Devstral-2-123B-Instruct-2512

mlx-community/Devstral-2-123B-Instruct-2512-8bit

This model mlx-community/Devstral-2-123B-Instruct-2512-8bit was converted to MLX format from mistralai/Devstral-2-123B-Instruct-2512 using mlx-lm version 0.28.4.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Devstral-2-123B-Instruct-2512-8bit")

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)