Refine open AI models using Hugging Face TRL
Refine open AI models using Hugging Face TRL


Author: Google Cloud Tech – Duration: 00:04:54
Tutorial: Refine Gemma 2 with Hugging Face TRL on GKE → https://goo.gle/3ZcLQiL
Containers Hugging Face Deep Learning → https://goo.gle/3Otahn3
Documents: Hugging Face TRL → https://goo.gle/3ZgsyJs
Supervised fine-tuning of a pre-trained language model teaches a model to improve at a certain task by showing it many examples of input and desired output. A smaller, fine-tuned model can actually outperform a much larger, general-purpose model on these specific tasks. Join Googler Wietse Venema as he dives into building open models using Hugging Face Transformer Reinforcement Learning (TRL) using Google Kubernetes Engine (GKE). More Resources: Learn about Efficient Parameter Tuning (PEFT) → https://goo.gle/4eUb6js
Watch more Google Cloud: Building with Hugging Face → https://goo.gle/BuildWithHuggingFace
Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech
#GoogleCloud #HuggingFace Speaker: Wietse Venema Products mentioned: Gemma, Google Kubernetes Engine (GKE)






