SWE Agent LM 32B 4bit

🚀 mlx-community/SWE-agent-LM-32B-4bit

The mlx-community/SWE-agent-LM-32B-4bit model is converted to MLX format from SWE-bench/SWE-agent-LM-32B, offering efficient text generation capabilities for software engineering agents.

🚀 Quick Start

Prerequisites

Installation

To use this model with MLX, you need to install the mlx-lm library:

pip install mlx-lm

💻 Usage Examples

Basic Usage

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/SWE-agent-LM-32B-4bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)