Deepseek Prover V2 7B Bf16

🚀 mlx-community/DeepSeek-Prover-V2-7B-bf16

This model converts the deepseek-ai/DeepSeek-Prover-V2-7B into the MLX format, offering enhanced performance and compatibility for text generation tasks.

🚀 Quick Start

This model mlx-community/DeepSeek-Prover-V2-7B-bf16 was converted to MLX format from deepseek-ai/DeepSeek-Prover-V2-7B using mlx-lm version 0.24.1.

📦 Installation

pip install mlx-lm

💻 Usage Examples

Basic Usage

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/DeepSeek-Prover-V2-7B-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)