TheDrummer-Skyfall-31B-v4-mlx-4Bit

mrtoots/TheDrummer-Skyfall-31B-v4-mlx-4Bit

The Model mrtoots/TheDrummer-Skyfall-31B-v4-mlx-4Bit was converted to MLX format from TheDrummer/Skyfall-31B-v4 using mlx-lm version 0.26.4.

Toots' Note:

Please follow and support TheDrummer's work if you like it!

🦛 <span style="color:#800080">If you want a free consulting session, </span>fill out this form <span style="color:#800080">to get in touch!</span> 🤗

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mrtoots/Skyfall-31B-v4-mlx-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)