Hey there! I'm a passionate 23-year-old backend developer currently working at Telefónica. My focus is on system design and architecture, with a strong interest in building scalable, robust microservices and distributed systems. I enjoy tackling complex challenges that require innovative architectural solutions. In addition, I'm deeply fascinated by artificial intelligence, particularly in areas such as intelligent agents and large language models (LLMs). I'm always exploring new technologies and ideas to push the boundaries of what's possible in the backend world.
TuneYourLlama is a platform for fine-tuning LLMs with private data, combining model tuning and RAG (Retrieval-Augmented Generation) for more accurate responses.
- Fine-tuning Hugging Face models with your own data (PDF, CSV).
- RAG to enhance responses using embeddings and vector databases.
- Real-time processing with Kafka and event queues.
- Distributed architecture with microservices, PostgreSQL, and integrated security.
- Interactive interface in React to monitor and manage training.
|
|
|
|
|
|