Tharun P's repositories
Movie-Recommendation-System-with-Sentiment-Analysis
This is a Machine Learning project to create a "Movie Recommender System" and predict user ratings for movies using cosine similarity.
WeatherBot
This is the bot that will give weather details of any place in the world.
3D-box-annotations-objects
A large-scale NOCS dataset for with ground truth annotations for data from different domains: outdoor scenes, indoor scenes, and object-centric videos.
awesome-social-agents
A collection of works that investigate social agents, simulations and their real-world impact in text, embodied, and robotics contexts.
composable_kernel
Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators
glue-factory
Training library for local feature detection and matching
home-robot
Mobile manipulation research tools for roboticists
lerobot
🤗 LeRobot: End-to-end Learning for Real-World Robotics in Pytorch
llama.cpp
LLM inference in C/C++
motion-diffusion-model
The official PyTorch implementation of the paper "Human Motion Diffusion Model"
Multi-Task_Robot-Learning
A visual behavior cloning agent for real-world multi-task robotic manipulation, successfully completing three tasks in two kitchens using a single policy and just five examples for each task
onnx-tensorrt
ONNX-TensorRT: TensorRT backend for ONNX
Optimize_RAG_Pipeline
Best practices with Milvus vector database using RAG pipeline.
Prometheus2_SFT_distillation
Prometheus 2 is an alternative of GPT-4 evaluation when doing fine-grained evaluation of an underlying LLM & a Reward model for Reinforcement Learning from Human Feedback (RLHF).
pytorch-lightning
Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.
rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
tinygrad
You like pytorch? You like micrograd? You love tinygrad! ❤️
TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.
Vista
A Generalizable World Model for Autonomous Driving