pytorch

Low-Resource LLM Fine-Tuning using Unsloth and LoRA/QLoRA (WSL2/Linux) 🧠

Runtime detector for reward hacking and misalignment in LLM agents (89.7% F1 on 5,391 trajectories).

Fast and practical image deraining with PyTorch.

Fine-Tuned Language Models Exploration using LoRA and Hugging Face's Transformers Library

FastText Pytorch version

This is a repository about Text Summarization

[ACL 2026 Oral] Official code, UIQ benchmark, and pretrained checkpoints for "Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval" (Yoo et al., Sogang University)

Official GitHub repository of the lecture "Multimodal Deep Learning for Recommendation", at the 2024 ACM RecSys Summer School

Exploring Visual Interpretability for Contrastive Language-Image Pretraining

基于Qwen2.5-VL-3B + QLoRA的智能驾驶场景结构化理解系统

Generate novel text - novel finetuned from skt KoGPT2 base v2 - 한국어

Landcover classification on sentinel-2 data with Prithvi, EfficientNet-Unet and OSM / CNES Landcover labels.

🎙️ CosyVoice LoRA 微调框架：LLM+Flow 联合训练，实现无 Prompt 语音合成

🤖 Deep Catalan: Bring closer the Catalan Language to Deep Learning using ULMFit.

Distributed model and API infrastructure for PyTorch and Hugging Face.

An HF's Smolagent to automate molecular dynamics simulations using GROMACS.

Code and dataset for paper - Application of Deep Learning in Generating Structured Radiology Reports: A Transformer-Based Technique

Containerized self-hosted REST API for vision classification, utilizing Hugging Face transformers.

Convert pretrained RoBerta models to various long-document transformer models

Experiments with multimodal deep learning models based on transformers