Yash Bonde's Projects
Simple Studio for AI Experiments
Stable Diffusion backend (hopefully FE) running on top of NimbleBox
Simple pure-python AST engine with lazy lookup and code traversal
Work done for Kaggle speech recognition challenge by Google Brain Team.
A curated list of awesome Deep Learning tutorials, projects and communities.
A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
These are the basic utilities and models that I find helpful in my ML work
π¦ Simplify the creation and management of prompt chains. Build complex chat applications using LLMs with 4 clicks β‘οΈ
Supervised Pre-training a chess engine on moves only, can it surpass me? Can it learn board representation internally? Can this learned vector be used with tree search? Is emergent behaviour really needed? Can I publish a paper on this?
Simple full stack project involving authentication + login + recording of games + DL training
PyTorch package for the discrete VAE used for DALLΒ·E.
When Dall E was a baby trained on a bit of data
Work done on DNC. Including it's implementation in supervised and reinforcement learning
This was made for the competition www.kaggle.com/c/dog-breed-identification
python-fire for internet
These are the codes for running complex models on devices such as Arduino or TI Launchpads
This is the learning environment for Freeciv 3.1 with python bindings for advancements in RL. This is the first project of it's kind in the world and will also be the most challenging environment out there.
This is the repo realted to the work done in main freeciv-python repo
This is a python binding for Freeciv-web, which is an Open Source strategy game. This provides an interface for AI agents to play this game.
This is just a simple implementation of GAN that can be used for TTS or text to speech translational models.
Can I use GAN to create game levels?
gperc or How to general purpose perceivers! Train models by just throwing data at it.