Few-shot Learning in Production
In this talk, you will learn how to:
– Train Sentence Transformers with little labeled data using a technique called SetFit recently released by Hugging Face and Intel Labs
– Compress models with knowledge distillation
– Accelerate inference with quantization and 🤗 Optimum and Intel® Neural Compressor
For more details about SetFit, check out the library 👉: https://github.com/huggingface/setfit
Moshe Wasserblat
NLP Research Manager INTEL
Moshe Wasserblat is the NLP DL Research Lead for Intel Lab Emergent AI group. Previously, he was with NICE Systems for more than 17 years, where he founded and led the speech and text analytics research team.
He has filed more than 60 patents in the field of language technology and has several publications in international conferences and journals.
