deepcogito-cogito-v1-preview-llama-8B-bf16/README.md

license, library_name, base_model, pipeline_tag, tags

license	library_name	base_model	pipeline_tag	tags
llama3.1	mlx	deepcogito/cogito-v1-preview-llama-8B	text-generation	mlx

mlx-community/deepcogito-cogito-v1-preview-llama-8B-bf16

This model mlx-community/deepcogito-cogito-v1-preview-llama-8B-bf16 was converted to MLX format from deepcogito/cogito-v1-preview-llama-8B using mlx-lm version 0.22.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/deepcogito-cogito-v1-preview-llama-8B-bf16")

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)