Generate instruction datasets for fine-tuning Large Language Models (LLMs) using lightweight libraries and documents.
Distilling key points after >2 years of experience and from AI developers’ own tutorials, hands-on and with examples.
Each time you run the model, the results may vary a little bit. Overall, after 5 tries, I can conclude that SBERT has a bit better performance in terms of best f1 score while Data2vec used way less memory. The average f1 scores for both models are very close.