📈 Predict market trends using a language model that reads stock charts as text, offering insights into price movements for better investment decisions.

Official implementation of "Resolving UnderEdit & OverEdit with Iterative & Neighbor-Assisted Model Editing" (EMNLP 2025 Findings).

💬 Analyze sentiment in real-time with this AI-powered web app, offering intuitive interface and robust model integration for text analysis.

🤖 Enhance your research efficiency with an AI-powered assistant that analyzes documents and provides insights through a smart multi-agent system.

🚀 Implement the Tiny Recursive Model (TRM) for improved performance in recursive tasks, building on the HRM framework by Sapient AI.

🌟 Implement Dreamer 4 for training agents within scalable world models, advancing the frontier of AI research and applications.

🧠 Generate and classify text in Spanish using deep learning techniques, enhancing your understanding of natural language processing applications.

🤖 Explore LocoFormer, a Transformer-XL model that enhances robot locomotion through long-context learning and real-world adaptability.

🔍 Fetch and analyze news from multiple sources with this powerful parser, offering insights through advanced content analysis and a modern web interface.

🔍 Visualize attention patterns in transformer models to better understand how LLMs process text inputs with interactive heatmaps and comparisons.

⚡ A seamless integration of HuggingFace Transformers & Diffusers with RBLN SDK for efficient inference on RBLN NPUs.

🌟 Pretrain domain-specific models using visual instructions to enhance accuracy and performance in specialized tasks with ViTP.

🌐 Translate English text to Hindi quickly using Python. Easily integrate and deploy with a simple API for seamless translation.

🖥️ Explore GPT-2 text generation with PyGPT2, a user-friendly Python app offering local model access, device selection, and prompt management.

📂 Extract, embed, cluster, and securely store Korean text from documents using BERT, enhancing research efficiency and organization.

💥 Optimize linear attention models with efficient Triton-based implementations in PyTorch, compatible across NVIDIA, AMD, and Intel platforms.

🔍 Conduct in-depth AI research with FastAPI, leveraging OpenAI models for idea validation, market analysis, and financial assessments.

🤖 Build an efficient customer support chatbot with zero-shot intent classification and modular skill handlers using FastAPI and Java.

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

Forensic Audio Classifier Tool is an ML-based digital forensics system built using PyTorch, Transformers, and a custom hybrid pipeline (Acoustic Model + Language Model + Classifier). It is designed for the Tripura Bengali dialect, enabling accurate transcription, keyword detection, and automated (Flagged / Review / Safe) audio classification.