Sovit Rath
Model Context Protocol (MCP) is a new standard by Anthropic to connect LLMs with different applications via a server-client protocol.
In this article, we explore OmniParser a UI screen parsing pipeline combining fine-tuned YOLO model for icon detection and Florence2 for icon recognition and icon description generation.
The NVIDIA AI Summit 2024, held from October 23 to 25 at the Jio World Convention Centre in Mumbai, marked a significant milestone in India’s journey toward becoming a global
In this article, we carry out handwritten text recognition using OCR. We fine tune the TrOCR model on the GNHK dataset.
In this article, we fine tune the Whisper ASR model on a custom dataset to recognize Air Traffic Control audio.
In this article, we explore SAM 2 (Segment Anything Model 2), for Promptable Visual Segmentation of objects in images and videos.
In this article, we using the Dreambooth technique to train Stable Diffusion 1.5 and teach it to generate images of a very specific species of cat.
In this article, we cover the Hugging Face Diffusers library for text-to-image, image-to-image, and image inpainting.
In this article, we do text summarization using T5 and fine-tune the model to build a Text Summarization Gradio app.
In this article, we are fine tuning the T5 model for Stack Overflow tag generation using the Hugging Face Transformer library.
In this post, we fine-tune BERT on Arxiv abstract classification dataset using the Hugging Face Transformers library.
In this article, we go through the introduction to BERT, including, its architecture, pretraining strategy, and inference
