Llama 2 is a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Meta fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use cases. The models outperform open-source chat models on most benchmarks they tested, and based on their human evaluations for helpfulness and safety, may be a suitable substitute for closedsource models. They provide a detailed description of their approach to fine-tuning and safety improvements of Llama 2-Chat in order to enable the community to build on their work and contribute to the responsible development of LLMs.
Llama 2 is a new family of pretrained and fine-tuned models with scales of 7 billion to 70 billion parameters. These models have demonstrated their competitiveness with existing open-source chat models, as well as competency that is equivalent to some proprietary models on evaluation sets. Although they still lag behind other models like GPT-4. They meticulously elaborated on the methods and techniques applied in achieving our models, with a heavy emphasis on their alignment with the principles of helpfulness and safety. To contribute more significantly to society and foster the pace of research, they have responsibly opened access to Llama 2 and Llama 2-Chat. As part of their ongoing commitment to transparency and safety, they plan to make further improvements to Llama 2-Chat in future work.
Retrieval Augmented Generation (RAG) allows us to keep Large Language Models (LLMs) up to date with the latest information, reduce hallucinations, and allow us to cite the original source of information being used by the LLM. They build the RAG pipeline using a Pinecone vector database, a Llama 2 13B chat model, and wrap everything in Hugging Face and LangChain code.
Llama 2 is the best-performing open-source Large Language Model (LLM) to date. James Brigg discovered how to use the 70B parameter model fine-tuned for chat (Llama 2 70B Chat) using Hugging Face transformers and LangChain. They show how to apply Llama 2 as a conversational agent within LangChain.
Brian Wang is a Futurist Thought Leader and a popular Science blogger with 1 million readers per month. His blog Nextbigfuture.com is ranked #1 Science News Blog. It covers many disruptive technology and trends including Space, Robotics, Artificial Intelligence, Medicine, Anti-aging Biotechnology, and Nanotechnology.
Known for identifying cutting edge technologies, he is currently a Co-Founder of a startup and fundraiser for high potential early-stage companies. He is the Head of Research for Allocations for deep technology investments and an Angel Investor at Space Angels.
A frequent speaker at corporations, he has been a TEDx speaker, a Singularity University speaker and guest at numerous interviews for radio and podcasts. He is open to public speaking and advising engagements.
I tried it on hugging face. The 7B variant was available, but it mostly gave nonsense answers.
Right now the 70B seems available. So asked a random question, also made up nonsense:
https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI/discussions/89
Brian you really need to break that bad habit of direct linking to ArXiv PDF’s. Paper abstract landing pages exist for a reason, particularly as this paper already has a V2.
https://arxiv.org/abs/2307.09288
and for the tinkerers, the actual model download site is here
https://ai.meta.com/llama/
https://ai.meta.com/resources/models-and-libraries/llama-downloads/
Please find and report instances of LLM/AI applied to Google Scholar data sets on chemistry, physics, biochemistry, medicine, and any one of a host of specific diseases or engineering objectives. I use my brain and Google Scholar to scour the literature and find solutions to old problems. AI could do much better than I do.
By personal communication AI was applied to the laser powered thermonuclear inertial fusion project at Lawrence Livermore National Laboratory. AI reported that the tritium filled capsules should be oval shaped not spherical. The physicists laughed. AI was correct.