Stars
AdalFlow: The library to build & auto-optimize LLM applications.
A toolbox to iNNvestigate neural networks' predictions!
Minimal reproduction of DeepSeek R1-Zero
QLoRA: Efficient Finetuning of Quantized LLMs
Train transformer language models with reinforcement learning.
Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch
OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)
Official implementation for "Automatic Chain of Thought Prompting in Large Language Models" (stay tuned & more will be updated)
PyTorch implementation of the InfoNCE loss for self-supervised learning.
Customizable implementation of the self-instruct paper.
Retrieval Augmented Generation (RAG) chatbot powered by Weaviate
Library for decoder-only models that addresses attention degeneration to reduce hallucinations.
A simple application that allows users to chat with local text files using LLMs managed by ollama
Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥
Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
⚛️ It is keras based implementation of siamese architecture using lstm encoders to compute text similarity
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
Python tutorials as Jupyter Notebooks for NLP, ML, AI
💫 Jupyter notebooks for spaCy examples and tutorials
Distances and representations of persistence diagrams
Simple renderer for use with MuJoCo (>=2.1.2) Python Bindings.
High performance implementation of Vietoris-Rips persistence.
Ripser++: GPU-accelerated computation of Vietoris–Rips persistence barcodes
Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin Delayed Deep Deterministic Policy Gradient (TD3) neural network, a robot learns to navigate to a random g…
A customisable 3D platform for agent-based AI research
A large annotated dataset of the common marmoset vocal repertoire
The essence of my research, distilled for reusability. Enjoy 🥃!
Official implementation of "Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks", NeurIPS 2021.