This is your work, valued

Gabriel Mongaras

Elite
@gmongaras

MTS at Magic and ML researcher. I force rocks to learn things.

gmongaras.me/

Diffusion_models_from_scratch. Creating a diffusion model from scratch in PyTorch to learn exactly how they work.

396

AI_Girlfriend. Creating a waifu

132

Stable-Diffusion-3-From-Scratch. A repo that attempts to train stable diffusion 3 from scratch

42

YOLOX_From_Scratch. Attempting to build YOLOX from scratch

32

Latent_Diffusion_Model_Imagenet2012. A latent flow-based diffusion model trained on the 2012 ImageNet dataset from scratch.

25

Cottention_Transformer. Code for the paper "Cottention: Linear Transformers With Cosine Attention"

20

Llama-2_Huggingface_4Bit_QLoRA. A working example of a 4bit QLoRA Falcon model using huggingface

11

AI_Girlfriend_Medium. Code that goes with my AI Girlfriend medium article.

10

PyTorchLite_Demo. Demo for PyTorch Lite on Android for an article I wrote on Medium

8

Wizard_QLoRA_Finetuning. Finetuning Some Wizard Models With QLoRA

7

On-the-Expressiveness-of-Softmax-Attention-A-Recurrent-Neural-Network-Perspective. Jupyter Notebook

4

AI_Girlfriend_Reduced. Reduced version of AI Girlfriend for faster downloading

4

Consistency_Models. Jupyter Notebook

3

Learnable_Rotary_Embeddings. Just some tests I ran

2

Anime_StyleGAN_Website. Website that uses StyleGAN2 to produce fake anime pictures.

2

GRPO-DAPO-Tests. Playing around with GRPO and DAPO

2

MetaU_Capstone. Get a fortune a day that can either be generated using an AI I built from scratch or by picking from a list of real fortunes. Then, add some friends and share your fortunes! This app was created for MetaU

1

Reinforcement_Learning_Stuff. I need to learn some RL

1

PPO_CartPole. Using PPO, I am attempting to solve the cartpole environment

1

Protogen_Code_Public. Public code for my protogen

1

Visualizing_Gradient_Descent_For_BCE_Loss. Using only numpy in Python, a neural network with a forward and backward method is used to classify given points (x1, x2) to a color of red or blue.

1

Dino_Game_AI_V2. AI that learns to play the Google dino game using an improved version of NEAT

1

GAN_TextGen. Attempting to use a GAN to generate random sentences

1

Dino_Game_AI. AI that learns to play the Google dino game

1

Token_Merging_Tests. Jupyter Notebook

1

Diffusion-TTS. Diffusion TTS - Synthesized voice using stable diffusion to map between noise and stylized speech

1