Pinned Repositories
Awesome-Image-Inpainting
A curated list of image inpainting and video inpainting papers and resources
CapsNet-Pytorch
Pytorch version of Hinton's Capsule Theory paper: Dynamic Routing Between Capsules
CDLA
CDLA: A Chinese document layout analysis (CDLA) dataset
deep-learning-for-image-processing
deep learning for image processing including classification and object-detection etc.
Gasyori100knock
画像処理100本ノックして画像処理を画像処理して画像処理するためのもの For Japanese, English and Chinese
Global-and-Local-Attention-Based-Free-Form-Image-Inpainting
Official implementation of "Global and local attention-based free-form image inpainting"
Hyper-Table-OCR
A carefully-designed OCR pipeline for universal boarded table recognition and reconstruction.
Learning-to-See-in-the-Dark
Learning to See in the Dark. CVPR 2018
ML-NLP
此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。
MPRNet
Official repository for "Multi-Stage Progressive Image Restoration" (CVPR 2021). SOTA results for image deblurring, deraining, and denoising.
tkone2018's Repositories
tkone2018/autogen
Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ
tkone2018/dbrx
Code examples and resources for DBRX, a large language model developed by Databricks
tkone2018/DISC-FinLLM
DISC-FinLLM，中文金融大语言模型（LLM），旨在为用户提供金融场景下专业、智能、全面的金融咨询服务。DISC-FinLLM, a Chinese financial large language model (LLM) designed to provide users with professional, intelligent, and comprehensive financial consulting services in financial scenarios.
tkone2018/DocRes
[CVPR 2024] DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks
tkone2018/embedding_rerank_retrieval
本项目是针对RAG中的Retrieve阶段的召回技术及算法效果所做评估实验。使用主体框架为LlamaIndex.
tkone2018/facechain
FaceChain is a deep-learning toolchain for generating your Digital-Twin.
tkone2018/FastGPT
FastGPT is a knowledge-based platform built on the LLM, offers out-of-the-box data processing and model invocation capabilities, allows for workflow orchestration through Flow visualization!
tkone2018/FinGPT
Data-Centric FinGPT. Open-source for open finance! Revolutionize 🔥 We release the trained model on HuggingFace.
tkone2018/GLEE
【CVPR2024】GLEE: General Object Foundation Model for Images and Videos at Scale
tkone2018/glm-cookbook
Zhipu API series cookbook
tkone2018/gorilla
Gorilla: An API store for LLMs
tkone2018/grok-1
Grok open release
tkone2018/Illumination-Adaptive-Transformer
[BMVC 2022] You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction. SOTA for low light enhancement, 0.004 seconds try this for pre-processing.
tkone2018/IntelliQ
Advanced Multi-Turn QA System with LLM and Intent Recognition. 基于LLM大语言模型意图识别、参数抽取结合slot词槽技术实现多轮问答、NL2API. 打造Function Call多轮问答最佳实践
tkone2018/KnowLM
An Open-sourced Knowledgable Large Language Model Framework.
tkone2018/Laws
tkone2018/llama_index
LlamaIndex (formerly GPT Index) is a data framework for your LLM applications
tkone2018/llama_parse
Parse files for optimal RAG
tkone2018/llm-action
本项目旨在分享大模型相关技术原理以及实战经验。
tkone2018/llm_4_doc_qa
本项目用于文档问答，使用向量嵌入 + ES 做召回，使用Rerank模型作为精排，再使用LLM做文档问答，Web框架使用Flask。
tkone2018/marker
Convert PDF to markdown quickly with high accuracy
tkone2018/Monkey
【CVPR 2024 Highlight】Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models
tkone2018/Open-Sora
Open-Sora: Democratizing Efficient Video Production for All
tkone2018/pycorrector
pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，LLaMA等模型应用在纠错场景，开箱即用。
tkone2018/QAnything
Question and Answer based on Anything.
tkone2018/RESDSQL
The Pytorch implementation of RESDSQL (AAAI 2023).
tkone2018/seamless_communication
Foundational Models for State-of-the-Art Speech and Text Translation
tkone2018/spRAG
RAG framework for challenging queries over dense unstructured data
tkone2018/TextHawk
Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models
tkone2018/Time-Series-Library
A Library for Advanced Deep Time Series Models.