tokarev-i-v

3d_masks

3d masks using three.js and facemesh by tensorflow.js

AI-QMIX

Code for "AI-QMIX: Attention and Imagination for Dynamic Multi-Agent Reinforcement Learning"

awesome-llm-rl-agents

List of sources related to llms, transformers and reinforcement learning agents

awesome-ml-cybersecurity

reasoning-lib

researchim

rllib.js

Reinforcement learning library with JavaScript.

tfjs-gans

There are collections of GANs made using tfjs and THREE.js

VK_NEXT_CHAT

3D Web chat, using Three.js + Peer.js + Node.js

webrtc_chat_3d_engine

There is Engine for creating web 3d chats. It is made using WebRTC (Peer.js) + WebGL (Three.js).

tokarev-i-v/researchim

tokarev-i-v/awesome-ml-cybersecurity

tokarev-i-v/algo

tokarev-i-v/cultural-accumulation

tokarev-i-v/dart-math

[NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*

tokarev-i-v/DeepCubeAI

Learning Discrete World Models for Heuristic Search

tokarev-i-v/grokfast

Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"

tokarev-i-v/GrokkedTransformer

Code for the paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'

tokarev-i-v/Grounding_LLMs_with_online_RL

We perform functional grounding of LLMs' knowledge in BabyAI-Text

tokarev-i-v/LAPO

Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)

tokarev-i-v/LightZero

[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios

tokarev-i-v/LLaMA-O1

Large Reasoning Models

tokarev-i-v/llm.c

LLM training in simple, raw C/CUDA

tokarev-i-v/loss-of-plasticity

Demonstrations of Loss of Plasticity and Implementation of Continual Backpropagation

tokarev-i-v/MacroHFT

tokarev-i-v/MathBlackBox

tokarev-i-v/mctslib

tokarev-i-v/models-at-home

tokarev-i-v/open-oasis

Inference script for Oasis 500M

tokarev-i-v/openr

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

tokarev-i-v/quiet-star

Code for Quiet-STaR

tokarev-i-v/RethinkMCTS

tokarev-i-v/rStar

tokarev-i-v/ScaleQuest

We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.

tokarev-i-v/search-agents

Code for the paper 🌳 Tree Search for Language Model Agents

tokarev-i-v/SelfCorrectionLanguageModelTraining

tokarev-i-v/Super_MARIO

tokarev-i-v/TheArtofHPC_pdfs

All pdfs of Victor Eijkhout's Art of HPC books and courses

tokarev-i-v/torax

TORAX: Tokamak transport simulation in JAX

tokarev-i-v/uvadlc_notebooks

Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2022/Spring 2022