seefun's Stars
openai/whisper
Robust Speech Recognition via Large-Scale Weak Supervision
xai-org/grok-1
Grok open release
PaddlePaddle/PaddleOCR
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
hiroi-sora/Umi-OCR
OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片,PDF文档识别,排除水印/页眉页脚,扫描/生成二维码。内置多国语言库。
JaidedAI/EasyOCR
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Stability-AI/generative-models
Generative Models by Stability AI
unslothai/unsloth
Finetune Llama 3.3, Mistral, Phi-4, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory
mlc-ai/mlc-llm
Universal LLM Deployment Engine with ML Compilation
UKPLab/sentence-transformers
State-of-the-Art Text Embeddings
ocrmypdf/OCRmyPDF
OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
Lightning-AI/litgpt
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
mistralai/mistral-inference
Official inference library for Mistral models
facebookresearch/nougat
Implementation of Nougat Neural Optical Understanding for Academic Documents
FlagOpen/FlagEmbedding
Retrieval and Retrieval-augmented LLMs
leptonai/search_with_lepton
Building a quick conversation-based search demo with Lepton AI.
google/gemma_pytorch
The official PyTorch implementation of Google's Gemma models
allenai/OLMo
Modeling, training, eval, and inference code for OLMo
langchain-ai/rag-from-scratch
wonderworks-software/PyFlow
Visual scripting framework for python - https://wonderworks-software.github.io/PyFlow
deepseek-ai/DeepSeek-VL
DeepSeek-VL: Towards Real-World Vision-Language Understanding
breezedeus/Pix2Text
An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.
NUS-HPC-AI-Lab/VideoSys
VideoSys: An easy and efficient system for video generation
VikParuchuri/texify
Math OCR model that outputs LaTeX and markdown
mit-han-lab/distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
OleehyO/TexTeller
TexTeller can convert image to latex formulas (image2latex, latex OCR) with higher accuracy and exhibits superior generalization ability, enabling it to cover most usage scenarios.
bojone/rerope
Rectified Rotary Position Embeddings
UniModal4Reasoning/ChartVLM
Official Repository of ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning
opendatalab/laion5b-downloader
deep-diver/paperqa-ui