Skip to content
AI Model Radar

Llama 3.1 Nemotron 70B Instruct HF

nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
Open Source · chat · open-weights
GA Alert me on changes
Context
131.1K
Max output
1K
Pricing
Open weights
Modalities
text
Released
12 Oct 2024
License: llama3.1 · nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
AI summary
● machine-written

Llama 3.1 Nemotron 70B Instruct open-weights model released by NVIDIA

Llama 3.1 Nemotron 70B Instruct is an open-weights language model built on Meta's Llama 3.1 architecture, enhanced with Reinforcement Learning from Human Feedback (RLHF) for improved alignment. It supports a 131,072-token context window and is designed for generating precise responses across diverse domains. The model was released on October 12, 2024, and is available for free use under the Llama 3.1 Community License.

What's new
  • 131,072 token context window (131K tokens)
  • RLHF-trained for improved helpfulness and response accuracy
  • Open weights; available on Hugging Face
  • Released October 12, 2024
Best for
High-accuracy customer support and helpfulness-focused applicationsLong-context document analysis and summarizationMulti-domain conversational AI requiring precise responses
Sources

Source: https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF