Llama 3.1 8B UltraLong 4M Instruct

🚀 Nemotron-UltraLong-8B

A series of ultra-long context language models that can process extensive text sequences while maintaining competitive performance on standard benchmarks.

🚀 Quick Start

Starting with transformers >= 4.43.0 onward, you can run conversational inference using the Transformers pipeline abstraction or by leveraging the Auto classes with the generate() function.

Make sure to update your transformers installation via pip install --upgrade transformers.

import transformers
import torch

model_id = "nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

outputs = pipeline(
    messages,
    max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])

✨ Features

We introduce Nemotron-UltraLong-8B, a series of ultra-long context language models designed to process extensive sequences of text (up to 1M, 2M, and 4M tokens) while maintaining competitive performance on standard benchmarks. Built on the Llama-3.1, UltraLong-8B leverages a systematic training recipe that combines efficient continued pretraining with instruction tuning to enhance long-context understanding and instruction-following capabilities. This approach enables our models to efficiently scale their context windows without sacrificing general performance.

📚 Documentation

The UltraLong Models

• nvidia/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct
• nvidia/Llama-3.1-Nemotron-8B-UltraLong-2M-Instruct
• nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct

Model Card

Evaluation Results

We evaluate Nemotron-UltraLong-8B on a diverse set of benchmarks, including long-context tasks (e.g., RULER, LV-Eval, and InfiniteBench) and standard tasks (e.g., MMLU, MATH, GSM-8K, and HumanEval). UltraLong-8B achieves superior performance on ultra-long context tasks while maintaining competitive results on standard benchmarks.

Needle in a Haystack

Long context evaluation

Standard capability evaluation

Correspondence to

Chejian Xu (chejian2@illinois.edu), Wei Ping (wping@nvidia.com)

Citation

@article{ulralong2025,
  title={From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models},
  author={Xu, Chejian and Ping, Wei and Xu, Peng and Liu, Zihan and Wang, Boxin and Shoeybi, Mohammad and Catanzaro, Bryan},
  journal={arXiv preprint},
  year={2025}
 }

📄 License

cc-by-nc-4.0