About The corresponding code from our paper " Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning" . Do not hesitate to open an issue if you run into any tro…

Nearest Neighbor Normalization (EMNLP 2024)

[EMNLP 2024] Official Implementation of DisGeM: Distractor Generation for Multiple Choice Question with Span Masking

Unofficial METU Presentation Template

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

Finetune Llama 3.2, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory

🔥 [CVPR2024] Official implementation of "Self-correcting LLM-controlled Diffusion Models (SLD)

Topic Summaries prepared by students as a part of the METU Deep Generative Models class.

Paper re-implementations from the course METU CENG796 Deep Generative Models.

[NeurIPS 2024] Official Implementation of CLIPAway

NONWESTLIT Project Codebase

PyTorch implementation of One-step Diffusion with Distribution Matching Distillation

A novel inpainting framework that can remove objects from images based on the instructions given as text prompts.

Course notes

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

A Python package for easy multiprocessing, but faster than multiprocessing

Tensor library for machine learning

Paper List for Contrastive Learning for Natural Language Processing

MinIO is a high-performance, S3 compatible object store, open sourced under GNU AGPLv3 license.

Windows compile of bitsandbytes for use in text-generation-webui.

Powerful torch based deep-learning framework with combination of tools from PyTorch-Lightning and HuggingFace.

Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.

Ship RAG based LLM web apps in seconds.

Inference Llama 2 in one file of pure C

PyTorch Implementation of STD Framework

Generative Models by Stability AI

Transformers w/o Attention, based fully on MLPs

CENG502 Spring2023 Projects

Ultralytics YOLO11 🚀

Pretrained models on CIFAR10/100 in PyTorch