Modelpublic

splats/Llama-3_3-Nemotron-Super-49B-v1_5-mlx-8Bit

sourceHugging Faceotherupdated 7mo agoView on Hugging Face

0likes33downloads

Model Card

splats/Llama-33-Nemotron-Super-49B-v15-mlx-8Bit

The Model splats/Llama-3_3-Nemotron-Super-49B-v1_5-mlx-8Bit was converted to MLX format from nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 using mlx-lm version 0.29.1.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("splats/Llama-3_3-Nemotron-Super-49B-v1_5-mlx-8Bit")

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)