Meta-Llama-3.1-8B-Instruct is a large language model released by Meta, released under the llama3.1 license, with a claimed knowledge cutoff of 2024-07-23. Its weights, configuration, and tokenizer files are shortlisted for hashing and on-chain attestation by Weight Registry.
Description
Meta's Llama 3.1 family launched July 2024 in a variety of sizes. This 8B instruct-tuned version is fast and efficient, extending context to 128K tokens and adding official multilingual support over Llama 3.
Metadata
Hugging Face stats
6,191,239 downloads on Hugging Face · 7,910 likes · pipeline: text-generation · library: transformers
Weight Hashes
Not yet hashed -- queued for processing.