rafapi
AI Alignment and Human-in-the-loop Machine Learning, focusing on the interplay between artificial intelligence and human-guided learning processes.
@ServiceNow ResearchLondon, UK
Pinned Repositories
baal
Bayesian active learning library for research and industrial usecases.
AI-Researcher
AI researcher - with a single query determine focus areas to investigate, searching the web and scraping content from relevant websites to do research autonomously.
alternative_article
contrastive_rl
fastapi-prophet
Stock Market predictions with Prophet and FastAPI
pomolux
Python API for Luxafor combined with a Pomodoro timer
PipelineRL
A scalable asynchronous reinforcement learning implementation with in-flight weight updates.
TapeAgents
TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle
rafapi's Repositories
rafapi/fastapi-prophet
Stock Market predictions with Prophet and FastAPI
rafapi/contrastive_rl
rafapi/AI-Researcher
AI researcher - with a single query determine focus areas to investigate, searching the web and scraping content from relevant websites to do research autonomously.
rafapi/alternative_article
rafapi/backend-microservices
Microservices using RabbitMQ as message broker
rafapi/blog
Source code of my personal blog
rafapi/fastapi_text_sum
Text Summarisation using FastAPI
rafapi/mvenv
A Python 3 Virtual Environment Management Tool
rafapi/summariser_client
A multi-platform client to consume the Summariser API
rafapi/custom-py-docker
Dockerfile with custom python indtall
rafapi/d4rl
A benchmark for offline reinforcement learning.
rafapi/faas-fns
FaaS functions
rafapi/finetuner
Finetuning any DNN for better embedding on neural search tasks
rafapi/frontend-microservices
rafapi/google-research
Google Research
rafapi/jax-rl
rafapi/Kalman-and-Bayesian-Filters-in-Python
Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filters, and more. All exercises include solutions.
rafapi/mjrl
Reinforcement learning algorithms for MuJoCo tasks
rafapi/nano-aha-moment
Single GPU, From Scratch (No RL Library), Efficient, Full Parameter Tuning Implementation of DeepSeek R1-Zero style training.
rafapi/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
rafapi/PipelineRL
A scalable asynchronous reinforcement learning implementation with in-flight weight updates.
rafapi/PMTG
rafapi/pytorch-a2c-ppo-acktr-gail
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
rafapi/question-answering
rafapi/rafapi
rafapi/rafapi.github.io
rafapi/stable-diffusion-webui
Stable Diffusion web UI
rafapi/thompson
Thompson Sampling Tutorial
rafapi/trl
Train transformer language models with reinforcement learning.
rafapi/whatsapp-mcp