cogito-v2-preview-llama-109B-MoE-q4-hi-mlx

This model cogito-v2-preview-llama-109B-MoE-q4-hi-mlx was converted to MLX format from deepcogito/cogito-v2-preview-llama-109B-MoE using mlx-lm version 0.26.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("cogito-v2-preview-llama-109B-MoE-q4-hi-mlx")

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)