Downloads · 30 days
66
9% of all-time downloads
Wwayu/Llama-3_1-Nemotron-Ultra-253B-v1-mlx-2Bit
Llama-3_1-Nemotron-Ultra-253B-v1-mlx-2Bit is a text generation model from Wwayu. 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 Wwayu/Llama-31-Nemotron-Ultra-253B-v1-mlx-2Bit was converted to MLX format from nvidia/Llama-31-Nemotron-Ultra-253B-v1 using mlx-lm version 0.26.4.
Downloads · 30 days
66
9% of all-time downloads
All-time downloads
735
Public
Parameters
253B
79.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors79.2 GB · 100%
How the weights are stored.
U32253B · 100%
From the Hugging Face model README
The Model Wwayu/Llama-3_1-Nemotron-Ultra-253B-v1-mlx-2Bit was converted to MLX format from nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 using mlx-lm version 0.26.4.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Wwayu/Llama-3_1-Nemotron-Ultra-253B-v1-mlx-2Bit")
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)