Instruction Fine Tuning

concepts · 2 notes linked

Related: Meta · Stanford · Large Language Models · Open Source AI · Llama · Georgi Gerganov · Model Quantization · Openai

Notes

• GitHub - tatsu-lab/stanford_alpaca: Code and documentation to train Stanford's Alpaca models, and generate the data. — Instruction-following LLaMA model fine-tuned via self-instruct data
• Why LLaMa Is A Big Deal — LLaMA enables GPT-3-class LLM inference on consumer hardware