Llama 2 is a collection of second-generation open-source Large Language Models (LLMs) from Meta, designed to handle a wide range of natural language processing tasks. These models range in scale from 7 billion to 70 billion parameters.
It is optimized for dialogue, has shown similar performance to popular closed-source models like ChatGPT and PaLM.
The repository implementation contains Text Generation on Pre-Trained NousResearch’s Llama-2-7b-chat-hf using guanaco-llama2-1k dataset.
This repo just contains my understanding on Llama2 LLM and trying to fine tune for faster text generation with minimal consumption of GPU compute resource.
Feel free to send issues if you face any problem.