Qvikhr 2.5 1.5B Instruct SMPO MLX 4bit

🚀 Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO_MLX-4bit

This model is a conversion to MLX format, enabling efficient use in relevant environments.

🚀 Quick Start

The Model Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO_MLX-4bit was converted to MLX format from Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO using mlx-lm version 0.21.1.

📦 Installation

pip install mlx-lm

💻 Usage Examples

Basic Usage

from mlx_lm import load, generate

model, tokenizer = load("Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO_MLX-4bit")

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

This project is licensed under the apache-2.0 license.

📚 Documentation