Oriel — AI & technology worth noticing, every day.

meta-llama/Meta-Llama-3-8B-Instruct

AI model · https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct

First seen by Oriel on .

AI summary

The Hugging Face page documents Meta-Llama-3-8B-Instruct, an 8B-parameter instruction-tuned text-generation model released April 18, 2024 under Meta’s custom community license.

  • Llama 3 uses an optimized autoregressive transformer with GQA; the instruction-tuned variant applies SFT and RLHF for helpfulness and safety.
  • It accepts text and generates text or code, with an 8k context length, 15T+ pretraining tokens, and a March 2023 knowledge cutoff.
  • The model targets commercial and research use in English, particularly assistant-like chat; use beyond English requires developer fine-tuning under the license and policy.
  • Redistribution requires the agreement, attribution, and “Built with Meta Llama 3”; products using it must follow the Acceptable Use Policy and cannot improve another LLM.
  • Licensees whose products exceeded 700 million monthly active users at release must request a separate license from Meta before exercising the agreement’s rights.

#llama 3 #large language models #transformers #model licensing

Generated by gpt-5.6-sol. Check the original for details.

Metric trends

Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained

Likes

Total likes reported by the source.

  • Hugging Face Models: 6,135, latest observation ; +67 over observed period since

Downloads (30d)

Rolling 30-day downloads. A change in this value is not new downloads during the observed period.

  • Hugging Face Models: 425,523, latest observation ; 0 over observed period since

Aliases

SourceExternal IDURL
Hugging Face Modelsmeta-llama/Meta-Llama-3-8B-Instructhttps://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct Read discussion