Code-Summary-Llama-3.2-3B-Instruct

bestler/Summary-Agent-Llama-3.2-3B-Instruct

The Model bestler/Summary-Agent-Llama-3.2-3B-Instruct was converted to MLX format from mlx-community/Llama-3.2-3B-Instruct using mlx-lm version 0.20.6.

Code Summaries

This model is fine-tuned with LoRA on the CodeXGlue Dataset on performing Code Summaries for python source code.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("bestler/Summary-Agent-Llama-3.2-3B-Instruct")

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)