- Islamabad,Pakistan
- https://www.linkedin.com/in/muhammadali3216/
Stars
LLM Council works together to answer your hardest questions
Official inference repo for FLUX.1 models
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
very good whiteboard infinite canvas SDK
End-to-end realtime stack for connecting humans and AI
Open-source live-chat, email support, omni-channel desk. An alternative to Intercom, Zendesk, Salesforce Service Cloud etc. 🔥💬
[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
HOPE-Image and HOPE-Video 6-DOF pose datasets.
Helpful utilities for working with s3, sagemaker and other AWS services
Designing transformers with different attention mechanisms from scratch
SuperResolution using ESRGAN architecture with custom loss
Deploying a Pytorch trained model on sagemaker, with well documented steps
How to parse Textract results for post-processing
This repo contains, my experimentation of semantic and instance segmentation.
Exploring LDA and NTM algorithms, and analyzing the results across few use cases.
My implementation of data structures and algorithms in Python.
Simple implementation of OpenPose for SinglePerson, and MultiPerson
In this I have implemented Spoken Digits Recognition, from a Medium post.
Distributed-Training on Sagemaker Notebook Instance
Stock Price Prediction as my Capstone Project
From scratch learning for RL, using Pytorch, and OpenAI Gym.
Deep dive into Graph Neural Nets
A package to fix JSON responses from ChatGPT
Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024
A procedural Blender pipeline for photorealistic training image generation