A collection of Digital Signal Processing notebooks with a wireless communications theme.
-
Updated
Jan 24, 2023 - Jupyter Notebook
GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — Build software better, together
#
quantisationHere are 25 public repositories matching this topic...Language: All
Filter by language
Sort: Most stars
Sort options
A collection of Digital Signal Processing notebooks with a wireless communications theme.
python spectrum frequency communication jupyter notebook dsp wireless filters ofdm modulation quantisation
Wii/GC texture encoder with palette support (png, jpeg, gif, bmp, tiff, tpl, tex0, plt0, bti)
gamecube gui-application wii cli-app palette-generation colour-palette quantisation colour-quantization
On the Effects of Quantisation on Model Uncertainty in Bayesian Neural Networks
My Tensorflow Notebook. In this notebooks I have implemented various kind of model optimisation techniques.
LoRA fine-tune and serve NVFP4 models on one DGX Spark (GB10, 128 GB UMA): text backbones via generic-family onboarding, plus VLMs (vision tower, or LLM+tower jointly via --train-target both) validated end-to-end on Pixtral and Nemotron-Omni. Fused Triton dequant; runtime-LoRA and merge serving.
ai nvidia triton moe lora nvidia-gpu fine-tuning peft mixture-of-experts quantisation vision-language-model vllm qlora local-ai fp4 nemotron gb10 nvidia-blackwell nvfp4 dgx-spark
Applying SDLC for JPEG compression project
JPEG Encoding with Discrete Cosine Transform, Quantisation & Run-Length Compression
This Repository Stores an empirical study conducted on Meta-Llama-3-8B-Instruct Model , Running on a Nvidia T4 16Gb . Quantizing it to 4-bit NF4 to reclaim 54% VRAM and accelerate Llama-3-8B generation up to 8.2x on Edge Hardware . with Negligible Loss in Model Quality . Benchmarks Showcase the Results of the Research .
Transcribe meeting audio and summarises.
Image compression codec based on JPEG implemented in python
A research based project to optimize the graph coloring problem using the quantisation part of image compression and come up with a solution which is better than conventional algorithms for graph coloring.
The art primitives Forge was missing: an indexed palette, a pixel canvas, draw ops, a delta undo stack, dithering, median-cut quantisation and sprite sheets.
javascript palette canvas offline-first pixel-art isometric dithering zero-dependency generative sprite-sheet single-file quantisation
Do compressed classroom LLMs keep their answers, not just their scores? Fidelity, confident error, semantic entropy and measured inference energy across three model families at three quantisation levels.
benchmark reproducibility energy-efficiency automated-assessment educational-technology model-compression hallucination edge-ai green-ai quantisation large-language-models llama-cpp ollama llm-evaluation semantic-entropy
Source code: C++, SFML, MATLAB. The aim of the project was to implement various quantization algorithms in C ++ and to compare them in terms of the quality of the obtained results and the time needed to perform the calculations. On the way I've created an app with very basic GUI.
Optimising train, inference and throughput of expensive ML models
On-device video super-resolution, 270p to 1080p: a 1.9M-parameter recurrent student trained with DRIFT's terms and QAT, ONNX, TensorRT INT8 and Core ML exports, and a Rust playback pipeline.
Simple dithering library in Rust, based on image-rs
Experiments in quantisation consisting of quantisation from scratch, bitsandbytes, and llama.cpp. [Assignment 4 of Advanced Natural Language Processing, IIIT-H Monsoon '24]
Reference implementation of DRIFT: an INT8 recurrent video super-resolution student whose quantisation drift is bounded by a contraction penalty, with long-rollout QAT.
A complete pipeline for deep learning model optimization via teacher fine-tuning, knowledge distillation, and 4-bit quantization. Built with PyTorch, Transformers, and BitsAndBytes.
Add this topic to your repoTo associate your repository with the quantisation topic, visit your repo's landing page and select "manage topics." |
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |