Downloads · 30 days
18
2% of all-time downloads
sjug/Llama-3_3-Nemotron-Super-49B-v1-8bit
Llama-3_3-Nemotron-Super-49B-v1-8bit is a text generation model from sjug. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as other.
This model sjug/Llama-33-Nemotron-Super-49B-v1-8bit was converted to MLX format from nvidia/Llama-33-Nemotron-Super-49B-v1 using mlx-lm version 0.23.2.
Downloads · 30 days
18
2% of all-time downloads
All-time downloads
722
Public
Parameters
49.9B
56.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors56.1 GB · 100%
How the weights are stored.
U3249.9B · 100%
From the Hugging Face model README
This model sjug/Llama-3_3-Nemotron-Super-49B-v1-8bit was converted to MLX format from nvidia/Llama-3_3-Nemotron-Super-49B-v1 using mlx-lm version 0.23.2.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("sjug/Llama-3_3-Nemotron-Super-49B-v1-8bit")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)