metalman3289/Llama3.2-Hermes.Dolphin.Coder-1B-mlx-4Bit

Name: Llama3.2-Hermes.Dolphin.Coder-1B-mlx-4Bit
Availability: InStock

The Model metalman3289/Llama3.2-Hermes.Dolphin.Coder-1B-mlx-4Bit was converted to MLX format from WithinUsAI/Llama3.2-Hermes.Dolphin.Coder-1B using mlx-lm version 0.31.2.

Use with mlx

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("metalman3289/Llama3.2-Hermes.Dolphin.Coder-1B-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)