Kaggle Competition Report: LLM Science Exam
Can LLMs answer scientific questions? See how Kaggle winners used LLMs and RAG!
Older English posts
Simulating Real-Time Chats using Flask's Server-Sent Events
Discover the power of Flask's Server-Sent Events for better developer's experience of chatbots.
Training A Not-So-Large Language Model for $50
What I cannot create, I do not understand. Let's train your own LLM!
Kaggle Competition Report: Stable Diffusion
How do you invert the text-to-image generation by Stable Diffusion? Let's take a look at the solutions by the winning teams.
torch.compile Benchmarked
PyTorch 2.0 introduced a new feature for JIT-compiling. How can it accelerate model training and inference?
How to Get a List of Email Addresses of Team Members in Microsoft Teams
Learn how to easily obtain a list of email addresses for team members.
Tuning Large Language Models with Reinforcement Learning on a Single GPU
A quick guide for RLHF using trlX, OPT-1.5B, and LoRA.
Year in Review: Deep Learning in 2022
Uncover the top deep learning advancements of 2022. A year-in-review of key research papers and applications.
Kaggle Competition Report: HuBMAP + HPA
HuBMAP + HPA was a competition on image segmentation with a twist in how to split the dataset. How did winners approach this problem?
How to Increase Shared Memory in Vertex AI Workbench
If you want more shm in Workbench, specify shm size in the "Metadata" pane when creating a notebook.