tbs17

Tracy Shen's starred repositories

promptfoo

Test your prompts, agents, and RAGs. Redteaming, pentesting, vulnerability scanning for LLMs. Improve your app's quality and catch problems. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.

Language:TypeScriptMIT378200

pathway

Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.

Language:PythonNOASSERTION286500

dspy

DSPy: The framework for programming—not prompting—foundation models

Language:PythonMIT1506900

langchain-pandas

Example of how to use LangChain and Vertex AI Generative AI to ask plain English questions about Pandas dataframes.

Language:Python400

uform

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

Language:PythonApache-2.098900

pdfplumber

Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.

Language:PythonMIT613000

unstructured-python-client

A Python client for the Unstructured hosted API

Language:PythonMIT6300

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Language:Jupyter NotebookMIT2397400

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

Language:PythonApache-2.01457000

InferSent

InferSent sentence embeddings

Language:Jupyter NotebookNOASSERTION227800

audio-examples

Sample audio files

300

EasyOCR

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Language:PythonApache-2.02308100

donut

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

Language:PythonMIT558700

llm-finetuning

Guide for fine-tuning Llama/Mistral/CodeLlama models and more

Language:PythonMIT49700

UniTAB

UniTAB: Unifying Text and Box Outputs for Grounded VL Modeling, ECCV 2022 (Oral Presentation)

Language:PythonMIT8400

examples

📝 Examples of how to use Neptune for different use cases and with various MLOps tools

Language:Jupyter NotebookMIT7500

cjm-yolox-pytorch

A PyTorch implementation of the YOLOX object detection model based on the mmdetection implementation.

Language:Jupyter NotebookMIT500

modal-examples

Examples of programs built using Modal

Language:PythonMIT66000

project-images-segmentation

Experiment tracking and model registry in the images segmentation project

Language:Jupyter NotebookMIT200

unitable

UniTable: Towards a Unified Table Foundation Model

Language:Jupyter NotebookMIT30200

SuperCLUE-RAG

中文原生检索增强生成测评基准

8200

MTL-TabNet

MTL-TabNet: Multi-task Learning based Model for Image-based Table Recognition

Language:PythonApache-2.08000

DCNv2_latest

DCNv2 supports decent pytorch such as torch 1.5+ (now 1.8+)

Language:C++BSD-3-Clause61600

CenterNet

Object detection, 3D detection, and pose estimation using center point detection:

Language:PythonMIT721700

pytorch-retinanet

RetinaNet in PyTorch

Language:Python99100

cocoapi

COCO API - Dataset @ http://cocodataset.org/

Language:Jupyter NotebookNOASSERTION603400

AdvancedLiterateMachinery

A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.

Language:C++Apache-2.0123900

tessdata

Trained models with fast variant of the "best" LSTM models + legacy models

Apache-2.0616300

tesseract

Tesseract Open Source OCR Engine (main repository)

Language:C++Apache-2.06005400

chug

Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.

Language:PythonApache-2.013900