Lightning-1.7B-mlx-5Bit

bradyclarke/Lightning-1.7B-mlx-5Bit

The Model bradyclarke/Lightning-1.7B-mlx-5Bit was converted to MLX format from TitleOS/Lightning-1.7B using mlx-lm version 0.29.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("bradyclarke/Lightning-1.7B-mlx-5Bit")

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)