Getting Hugs, Fine-Tuning, and Avoiding the AI API Dependency Trap with Hugging Face’s Jeff Boudier
Description
In this episode of ODSC’s Ai X Podcast, Jeff Boudier of Hugging Face joins us to discuss Hugging Face’s new “Hugs” service for deploying AI, among other new Hugging Face developments. He’ll also go into detail about fine-tuning for model performance, the evolution of AI agents, and the challenges faced when deploying AI models into production.
Jeff Boudier is the Head of Product at Hugging Face, the #1 open platform for AI builders.
Previously, Jeff was a co-founder of Stupeflix, acquired by GoPro, where he served as director of Product Management, Product Marketing, Business Development, and Corporate Development.
Show Questions:
- Details about Hugging Face’s new 'Hugs' service for deploying AI.
- Hugging Face’s mission and how it is evolving with AI advancements.
- How fine-tuning is helping enterprises improve model performance.
- Gathering community feedback and managing fast-moving developments.
- Staying ahead of rapid AI advancements in the open-source realm.
- How Hugging Face is making it easier to fine-tune models.
- Hugging Face’s support for Retrieval-Augmented Generation (RAG).
- Challenges enterprises face when deploying AI models to production.
- The evolution of AI agents alongside large language models.
- Hugging Face’s integrations with other platforms and AI agents.
- The importance of privacy in running AI models locally.
- Concerns about models overfitting to academic benchmarks.
- Shifting benchmarks toward real-world production performance.
- Jeff’s upcoming session at ODSC West.
- Where to follow Jeff Boudier and Hugging Face.
Show Notes:
- Jeff’s upcoming session at ODSC West, “How to Build Your Own AI with Open Source and Hugging Face”: https://odsc.com/speakers/how-to-build-your-own-ai-with-open-source-and-hugging-face/
- Jeff’s Twitter/X: https://x.com/jeffboudier
- LinkedIn: https://www.linkedin.com/in/jeffboudier/
- HuggingChat: https://huggingface.co/chat/
- PEFT: State-of-the-art Parameter-Efficient Fine-Tuning: https://github.com/huggingface/peft
- Hugging Face Spaces: https://huggingface.co/spaces
- LLM Evaluation Guide: https://github.com/huggingface/evaluation-guidebook?tab=readme-ov-file
- LoRA: Low-Rank Adaptation of Large Language Models: https://arxiv.org/abs/2106.09685
- DPO: Direct Preference Optimization: https://arxiv.org/abs/2305.18290
- Open LLM Leaderboard: https://huggingface.co/open-llm-leaderboard
- LLM Guardrails: https://github.com/dottxt-ai/outlines
This episode was sponsored by:
Ai+ Training https://aiplus.training/
Home to hundreds of hours of on-demand, self-paced AI training, ODSC interviews, free webinars, and certifications in in-demand skills like LLMs and Prompt Engineering
And created in partnership with ODSC https://odsc.com/
The Leading AI Training Conference, featuring expert-led, hands-on workshops, training sessions, and talks on cutting-edge AI topics and tools, from data science and machine learning to generative AI to LLMOps
Never miss an episode, subscribe now!