LLM EXPLORER 57,252 MODELS INDEXED

Llama 3.1 Nemotron 70B Instruct by nvidia

By nvidia · 70 downloads
HF Repo ↗ Copy URL

Llama 3.1 Nemotron 70B Instruct is an open-source language model by nvidia. Features: 70b LLM, Context: 128K, License: llama3.1, Instruction-Based, LLM Explorer Score: 0.3, ELO: 1299.

  Arxiv:2310.05344   Arxiv:2311.09528   Arxiv:2406.08673   Arxiv:2410.01257 Base model:finetune:meta-llama... Base model:meta-llama/llama-3....   Dataset:nvidia/helpsteer2   En   Instruct   Llama3.1   Nemo   Nvidia   Region:us
Model Card on HF 🤗: https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct 

Llama 3.1 Nemotron 70B Instruct Benchmarks

LMSys ELO 1299 vs 1272 (so35) 2.1%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Llama 3.1 Nemotron 70B Instruct Parameters and Internals

Model Type 
Text Generation
Use Cases 
Areas:
Research, Commercial Applications
Additional Notes 
This model is a demonstration of our techniques for improving helpfulness in general-domain instruction following. It has not been tuned for performance in specialized domains such as math.
Supported Languages 
en (high)
Training Details 
Data Sources:
Human, Synthetic
Methodology:
REINFORCE
Model Architecture:
Transformer
Input Output 
Input Format:
String
Accepted Modalities:
Text
Output Format:
String
Release Notes 
Version:
v1.0
LLM NameLlama 3.1 Nemotron 70B Instruct
Repository 🤗https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct 
Base Model(s)  meta-llama/Llama-3.1-70B-Instruct   meta-llama/Llama-3.1-70B-Instruct
Model Size70b
Updated2026-08-04
Maintainernvidia
Instruction-BasedYes
Supported Languagesen
Licensellama3.1
Context Length131072
Model Max Length131072