Segmented and Gaze Controlled decompression for streaming displays such as VR

Quantized training using Keras

Incrementally partition data into `k` clusters.

Nim api-wrapper for llm-inference chatllm.cpp

kotlin api wrapper for llm-inference chatllm.cpp

A pretty way to compress images

EfficientNetV2 (Efficientnetv2-b2) and quantization int8 and fp32 (QAT and PTQ) on CK+ dataset . fine-tuning, augmentation, solving imbalanced dataset, etc.

Training neural network weights in a bitwise fashion: https://arxiv.org/abs/2202.09571

A library to help with the development of AI models with Keras, with a focus on edge / IoT applications. Based originally on https://github.com/yingkaisha/keras-unet-collection

Fine tuning of a model for AIMO 2 math competition on Kaggle

Running the Multimodal AI Chat App with Ollama using a locally loaded model

Running the Multimodal AI Chat App with LM Studio using a locally loaded model

ArtQuantization is developed for quantizing Large Language Models, focusing on optimizing the memory usage and performance. This repository provides experimental results of quantizing models such as Qwen2.5 using different algorithms like AWQ and GPTQ, and demonstrates the memory requirements under various graphics card configurations.

TrackNetV3 modified version (TensorRT INT8 Optimization)

Regularized Classification-Aware Quantization

Documentation of my notes, learnings, presentations on Computer vision and some other cool stuff

JNI wrapper for rwkv.cpp