llama3.1-typhoon2-8b-instruct-mlx-4bit

Float16-cloud/llama3.1-typhoon2-8b-instruct-mlx-4bit

The Model Float16-cloud/llama3.1-typhoon2-8b-instruct-mlx-4bit was converted to MLX format from scb10x/llama3.1-typhoon2-8b-instruct using mlx-lm version 0.20.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate
model, tokenizer = load("Float16-cloud/llama3.1-typhoon2-8b-instruct-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)