Deepcogito Cogito V1 Preview Llama 70B 6bit

🚀 mlx-community/deepcogito-cogito-v1-preview-llama-70B-6bit

This project provides a model converted to MLX format, which solves the problem of using the original model in the MLX environment and enables more efficient text generation tasks.

🚀 Quick Start

This model mlx-community/deepcogito-cogito-v1-preview-llama-70B-6bit was converted to MLX format from deepcogito/cogito-v1-preview-llama-70B using mlx-lm version 0.22.3.

📦 Installation

pip install mlx-lm

💻 Usage Examples

Basic Usage

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/deepcogito-cogito-v1-preview-llama-70B-6bit")

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)

📄 License

• License: llama3.1