Modelpublic

NexVeridian/Equinox-31B-8bit

sourceHugging Faceapache-2.0updated 23d agoView on Hugging Face

0likes40downloads

Model Card

NexVeridian/Equinox-31B-8bit

This model NexVeridian/Equinox-31B-8bit was converted to MLX format from LatitudeGames/Equinox-31B using mlx-lm version 0.32.0.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("NexVeridian/Equinox-31B-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, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)