Llama-2-7B is Meta's 7 billion parameter large language model from the Llama 2 family. Hosted on Hugging Face by NousResearch, it supports text generation and can be fine-tuned for downstream tasks. The model is compatible with Transformers, vLLM, and other popular inference frameworks.
In the Foundation models & chat space, Llama 2 7b Hf takes a focused approach. It focuses on accessing a high-quality open foundation model for commercial and research use without closed-source restrictions. It is built as an open-source project for developers and researchers. Llama 2 7b Hf is open source under the Open Source license. Llama 2 7b Hf is available on the web, the command line, and API.
It is developed by Meta (United States), and the product first shipped in 2023. Development happens publicly on GitHub with 59.5k stars. Key capabilities include Text Generation, Instruction Following, and Multiple Framework Support. It exposes integrations via a public API.
Latest indexed changes and source events
NousResearch/Llama-2-7b-hf verified by the PulseGate indexer
Other apps tracked under the same category.