pytorch

[ICML 2026] GRACE-VLM: deployable INT4 Qwen3-VL via quantization-aware distillation.

[SIGIR 2022] Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion

This repository contains all the work that I regularly did and studied from Medium blogs, several research papers, and other Repos (related/unrelated to the research papers).

Deploy BERT for Sentiment Analysis as REST API using FastAPI, Transformers by Hugging Face and PyTorch

🚀 200倍速！AI时代的下载神器 | Docker/PyPI/HuggingFace/CRAN 全加速 | 并行分片+智能缓存，让下载飞起来

OpenTextClassification is all you need for text classification! Open text classification for everyone, enjoy your NLP journey! 这可能是目前为止最全面的开源文本分类项目，支持中英双语、多种模型、多种任务。

PyTorch code for "VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks" (CVPR2022)

Pytorch-Named-Entity-Recognition-with-transformers

(TPAMI 2023) Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer

Implementation of CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.

A Toolkit for OpenAI's Consistency Models.

A Python package housing a collection of deep-learning multi-modal data fusion method pipelines! From data loading, to training, to evaluation - fusilli's got you covered 🌸

基于PyTorch的BERT中文文本分类模型（BERT Chinese text classification model implemented by PyTorch）

🦅 Pretrained BigBird Model for Korean (up to 4096 tokens)

A guided tour on how to use HuggingFace large language models on Macs with Apple Silicon

Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)

Distillation of KoBERT from SKTBrain (Lightweight KoBERT)

Cross-platform installer for Triton and SageAttention on ComfyUI. Simplifies GPU-accelerated inference setup for Windows users with automated dependency management and RTX 5090 support.

HugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision