koulanurag
Follow
Stars
Reference implementation for DPO (Direct Preference Optimization)
The source code for the gym-microrts paper.
Code for the paper Fine-Tuning Language Models from Human Preferences
A curated list of reinforcement learning with human feedback resources (continually updated)
Cramming the training of a (BERT-type) language model into limited compute.
Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".
Chain-of-Hindsight, A Scalable RLHF Method
A native PyTorch Library for large model training
Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.
maze datasets for investigating OOD behavior of ML systems
Examples and guides for using the OpenAI API
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
A library for advanced large language model reasoning
A benchmark for evaluating learning agents based on just language feedback
Fast bare-bones BPE for modern tokenizer training
The official PyTorch implementation of Google's Gemma models
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
(ECCV 2024) Code for V-IRL: Grounding Virtual Intelligence in Real Life
Official code for "Reward-Free Curricula for Training Robust World Models", ICLR 2024.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
DQN Zoo is a collection of reference implementations of reinforcement learning agents developed at DeepMind based on the Deep Q-Network (DQN) agent.
Benchmark for "Offline Policy Comparison with Confidence"
SDK for creating whiteboards and canvas experiences on the web.