Haseebasif7/cir-siglip
Three complementary item retrieval heads compared at matched conditions over one frozen SigLIP backbone. Polyvore Outfits
CS Sopho
Repositories
Haseebasif7/Haseebasif7.github.io
Haseebasif7/world-model-mcp
A world model in your agent's toolbox - see what happens before it does.
Haseebasif7/shellsim
Haseebasif7/qalb-posttrain
Haseebasif7/NeuroInk
🎨 NeuroInk - Neural style transfer Algorithm using VGG19. Blends content from one image with the style of another to create AI-generated artwork Using Pytorch
Haseebasif7/Load_Forecasting
Haseebasif7/VSM-IR
Vector Space Model for Information Retrieval
Haseebasif7/BotX-Discord-
BotX is an advanced Discord chatbot built with discord.py, featuring 24/7 hosting on Pylexnodes. It offers dynamic responses powered by the Mistral AI model, voice interaction with Google Text-to-Speech (gTTS) and FFmpeg, and an interactive help menu. Enhance your Discord server with BotX's sophisticated features.
Haseebasif7/Bolean-IR-Model
Haseebasif7/AuraSync
Haseebasif7/GEOPAK
🇵🇰 Province aware hierarchical image geolocation for Pakistan using dual vision encoders and geocell based inference
Haseebasif7/trl
Train transformer language models with reinforcement learning.
Haseebasif7/Fake-News-Prediction-SVM-
Developed a fake news prediction model using Support Vector Machine (SVM) and achieved an impressive 99.8% accuracy on the training dataset. The text preprocessing included stemming to normalize words, followed by the use of TF-IDF vectorization to convert the text data into numerical form
Haseebasif7/UrduReason-Eval
UrduReason-Eval: A comprehensive evaluation dataset with 800 Urdu reasoning problems across 6 categories (arithmetic, logical deduction, temporal, comparative, and causal reasoning) for assessing reasoning capabilities in Urdu language models.
Haseebasif7/Haseebasif7
Config Files for Readme
Haseebasif7/trackio
A lightweight, local-first, and 🆓 experiment tracking library from Hugging Face 🤗
Haseebasif7/transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Haseebasif7/dia
A TTS model capable of generating ultra-realistic dialogue in one pass.
Haseebasif7/Portfolio
Haseebasif7/EComRecSys
Haseebasif7/Multiview-Fusion-Transformer-Model
Haseebasif7/blueberry-llm
Haseebasif7/SurfAgent
SurfAgent is an AI agent built from scratch that performs web searches using Selenium and Brave Search, Langchain and supports GROQ or OLLAMA providing reliable sources for the results.
Haseebasif7/GeoSpatial-Copilot
Haseebasif7/VizDoom_RL
A PPO trained agent for VizDoom’s “Defend the Center” scenario, using a custom Gym wrapper and StableBaselines3
Haseebasif7/GAN
Collection of Notebooks from DeepLearning.AI GANs Specialization
Haseebasif7/DeepFaceEdit
This project enables the inversion of real facial images into the latent space of StyleGAN2-ADA, leveraging dlib based facial landmark detection for accurate alignment, and supports semantic attribute editing through controlled latent vector perturbations along interpretable directions
Haseebasif7/Image2Depth
A PyTorch implementation of the Pix2Pix architecture for image-to-image translation, tailored for depth estimation from dashboard camera images
Haseebasif7/NeRF
A PyTorch reimplementation of Neural Radiance Fields (NeRF) for 3D scene reconstruction from 2D images