Llama 3.1 Nemotron 70B Instruct
Zero-eval
#1GSM8K Chat
#1MMLU Chat
#1Instruct HumanEval
+1 more
by NVIDIA
+
+
+
+
About
Llama 3.1 Nemotron 70B was developed by NVIDIA through customization of Meta's Llama 3.1 70B, designed to enhance performance for specific use cases and deployments. Built with NVIDIA's optimizations and fine-tuning expertise, it demonstrates how foundation models can be adapted for specialized applications.
+
+
+
+
Timeline
AnnouncedOct 1, 2024
ReleasedOct 1, 2024
Knowledge CutoffDec 1, 2023
+
+
+
+
License & Family
License
Llama 3.1 Community License
Base ModelLlama 3.1 70B Instruct
Performance Overview
Performance metrics and category breakdown
Overall Performance
11 benchmarks
Average Score
67.9%
Best Score
91.4%
High Performers (80%+)
6+
+
+
+
All Benchmark Results for Llama 3.1 Nemotron 70B Instruct
Complete list of benchmark scores with detailed information
| GSM8k | text | 0.91 | 91.4% | Self-reported | |
| HellaSwag | text | 0.86 | 85.6% | Self-reported | |
| Winogrande | text | 0.85 | 84.5% | Self-reported | |
| GSM8K Chat | text | 0.82 | 81.9% | Self-reported | |
| MMLU Chat | text | 0.81 | 80.6% | Self-reported | |
| MMLU | text | 0.80 | 80.2% | Self-reported | |
| Instruct HumanEval | text | 0.74 | 73.8% | Self-reported | |
| ARC-C | text | 0.69 | 69.2% | Self-reported | |
| TruthfulQA | text | 0.59 | 58.6% | Self-reported | |
| XLSum English | text | 0.32 | 31.6% | Self-reported |
Showing 1 to 10 of 11 benchmarks
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+