Fine-tuning LLMs with Hugging Face SFT 🤗

Description

Topics that will be covered:

✅  Specialized Fine-Tuning: Adapt LLMs for niche tasks using labeled data.

  Introduction to Instruction Tuning: Enhance LLM capabilities and controllability.

✅  Dataset Preparation: Format datasets for effective instruction tuning.

✅  BitsAndBytes & Model Quantization: Optimize memory and speed with the BitsAndBytes library.

✅  PEFT & LoRA: Understand the benefits of the PEFT library from HuggingFace and the role of LoRA in fine-tuning.

✅  TRL Library Overview: Delve into the TRL (Transformers Reinforcement Learning) library’s functionalities.

LLMOps.Space LLMOps.Space

Deepchecks is a founding member of LLMOps.Space, a global community for LLM
practitioners. The community focuses on LLMOps-related content, discussions, and
events. Join thousands of practitioners on our Discord.
Join Discord ServerJoin Discord Server