Luca MassaronData Science AI Assistant with Gemma 2b-it: a RAG 101Demystifying Retrieval-Augmented Generation pipelines by building a data science assistant25 min read·May 9, 2024----
Luca MassaronSherlock Holmes Q&A Enhanced with Gemma 2b-it Fine-TuningFind how fine-tuning can be an alternative to building a RAG14 min read·Apr 14, 2024----
Luca MassaronML Olympiads: detect hallucinations in LLMs with Google GeminiDetecting hallucinations is challenging, gut Google Gemini can help7 min read·Mar 31, 2024----
Luca MassaronHigher performance with GemmaGoogle has unveiled Gemma 2B and 7B, two open-source AI models designed for smaller tasks such as simple chatbots or summarizations. Unlike…2 min read·Feb 21, 2024----
Luca MassaronFine-tuning a large language model on Kaggle Notebooks for solving real-world tasks — part 5…The final installment of this series where we save our fined-tuned model and reuse it for our applications.4 min read·Feb 20, 2024--1--1
Luca MassaronFine-tuning a large language model on Kaggle Notebooks for solving real-world tasks — part 4…An update on the best way to fine-tune LLMs such as LLama 2, Mistral 7B Instruct v0.2, or Phi-2, using consumer-grade GPUs or free online…5 min read·Feb 5, 2024----
Luca MassaronFine-tuning a large language model on Kaggle Notebooks for solving real-world tasks — part 3Reprising hands-on fine-tuning for financial sentiment analysis with Mistral 7B Instruct v0.2 and Phi-24 min read·Dec 18, 2023----
Luca MassaronFine-tuning a large language model on Kaggle Notebooks for solving real-world tasks — part 2Hands-on fine-tuning for financial sentiment analysis9 min read·Oct 23, 2023----
Luca MassaronFinetuning a large language model on Kaggle Notebooks for solving real-world tasks — part 1Some theory and ideas on adapting LLMs to your needs5 min read·Oct 23, 2023----