-
University of Freiburg
- Freiburg, Germany
- https://shobhitkr.vercel.app/
- @shobhit_speaks
Highlights
- Pro
Starred repositories
Lightweight coding agent that runs in your terminal
Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve existing models like BERT.
This repository offers a comprehensive overview and quantitative benchmarking of positional encoding methods in transformer-based time series models.
A universal time series representation learning framework
Chronos: Pretrained Models for Time Series Forecasting
A unified, modular Framework for Prompt Optimization
We introduce CAPO, a novel prompt optimization algorithm that integrates racing and multi-objective optimization for cost-efficiency and leverages few-shot examples and task descriptions, outperfor…
This repo contains the source code for the paper "Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning"
A collection of smart contracts used in the ENVITED ecosystem.
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
Learning to Estimate Shapley Values with Vision Transformers
Zero-shot Time Series Forecasting with TabPFN (work accepted at NeurIPS 2024 TRL and TSALM workshops)
🍯 T-Pot - The All In One Multi Honeypot Platform 🐝
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
Fast and Accurate ML in 3 Lines of Code
Official implementation of the CVPR 2024 paper ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions.
The interactive graphing library for Python ✨
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
[ICRA2024] Few-Shot Panoptic Segmentation With Foundation Models
PyTorch code and models for V-JEPA self-supervised learning from video.
Neural Pipeline Search (NePS): Helps deep learning experts find the best neural pipeline.
The world’s fastest framework for building websites.
⚡ TabPFN: Foundation Model for Tabular Data ⚡