llama-7b is a 7 billion parameter autoregressive language model based on the original LLaMA architecture. Hosted on Hugging Face by huggyllama, it supports text generation, instruction following, and conversational use cases. The model can be run locally with libraries such as Transformers or llama.cpp and is popular for research and on-device inference.
Llama 7b sits in PulseGate's Foundation models & chat category. It focuses on enabling local deployment and experimentation with a capable open-source large language model. It is built as an open-source project for developers. The project is open source (Open Source). It runs on the web, the command line, and API.
Behind Llama 7b is huggyllama, and it first shipped in 2023. Key capabilities include Text Generation, Chat Templates, and Instruction Following.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do