Train your own large language model quickly: fine-tuning of lora instructions based on LLAMA-7B

catalogs 1. Selected works: lit-llama2. Downloading the project3. Installation environment4. Download the LLAMA-7B model5. Doing model conversions6. Preliminary testing7. Why is instruction fine-tuning necessary?8. Commencement of instruction fine-tuning8.1 Data preparation8.2 Starting Model Training8.3 Model Testing Preface: System: ubuntu 18.04Graphics card: A100-80G (dabble, hehehe~) (This time the main record is how to quickly fine-tune commands for […]