Downloads · 30 days
40
3% of all-time downloads
LogicBombaklot/Llama-3_3-Nemotron-Super-49B-v1_5-mlx-8Bit
Llama-3_3-Nemotron-Super-49B-v1_5-mlx-8Bit is a text generation model from LogicBombaklot. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
The Model LogicBombaklot/Llama-33-Nemotron-Super-49B-v15-mlx-8Bit was converted to MLX format from nvidia/Llama-33-Nemotron-Super-49B-v15 using mlx-lm version 0.26.3.
Downloads · 30 days
40
3% of all-time downloads
All-time downloads
1.3K
Public
Parameters
49.9B
53 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors53 GB · 100%
How the weights are stored.
U3249.9B · 100%
From the Hugging Face model README
The Model LogicBombaklot/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 0.26.3.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("LogicBombaklot/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)