Explication des composants d'un petit LLM: données/dataset, tokenisation, architecture du modèle et processus d'entraînement.

Ever wondered what actually happens when you call an LLM API? This talk breaks down the inference pipeline from tokenization to text generation, explaining what's really going on under the hood. He will walk through the key sampling strategies and their parameters - temperature, top-p, top-k, beam search. We'll also cover performance tricks like quantization, KV caching, and prompt caching that can speed things up significantly. If time allows, we will also touch on some use-case-specific techniques like pass@k and majority voting.

A session exploring the Fabric-X endorsement phase, how it differs from the traditional Hyperledger Fabric model, and implications for developers. We'll cover tokenization use cases, hands-on examples, and practical deployment strategies using Ansible and Kubernetes.

A session focusing on the endorsement phase of Fabric-X, comparing it to traditional Hyperledger Fabric, with hands-on examples showing how the new model streamlines development for tokenization use cases and on-chain asset transfer. The session will also cover practical deployment strategies using Ansible and Kubernetes.

A deep dive into the Fabric-X endorsement phase, highlighting how it differs from the traditional Hyperledger Fabric model. Through hands-on examples, we’ll demonstrate how the new model streamlines development for designing decentralized applications and tokenization use cases.

In this session, we’ll take a deep dive into the endorsement phase of Fabric-X, highlighting how it differs from the traditional Hyperledger Fabric model and what these changes mean for developers. Through hands-on examples, we’ll demonstrate how the new model streamlines development and unlocks exciting possibilities for designing decentralized applications. We’ll also explore how to build applications tailored for tokenization use cases.

RWAs tokenization and real-world use cases.