Pinned Repositories
attention-module
Official PyTorch code for "BAM: Bottleneck Attention Module (BMVC2018)" and "CBAM: Convolutional Block Attention Module (ECCV2018)"
Attention_ocr.pytorch
This repository implements the the encoder and decoder model with attention model for OCR
caffe_ocr
主流ocr算法研究实验性的项目，目前实现了CNN+BLSTM+CTC架构
caffe_ocr_for_linux
crnn_chinese_characters_rec
chinese characters recognition
PyTorch-SE-ResNet
SE-ResNet PyTorch Version
SwinTextSpotter
Pytorch re-implementation of Paper: SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition (CVPR 2022)
text_renderer
Generate text images for training deep learning ocr model
Tianchi-FFT2
Tianchi Competition "Forgeries and Forensics" Track 2
trocr-chinese
transformers ocr for chinese
vincezengqiang's Repositories
vincezengqiang/CareGPT
🌞 CareGPT (关怀GPT)是一个医疗大语言模型，同时它集合了数十个公开可用的医疗微调数据集和开放可用的医疗大语言模型，包含LLM的训练、测评、部署等以促进医疗LLM快速发展。Medical LLM, Open Source Driven for a Healthy Future.
vincezengqiang/chatbot-ui
An open source ChatGPT UI.
vincezengqiang/ChatLaw
中文法律大模型
vincezengqiang/CTranslate2
Fast inference engine for Transformer models
vincezengqiang/DAMO-ConvAI
DAMO-ConvAI: The official repository which contains the codebase for Alibaba DAMO Conversational AI.
vincezengqiang/direct-preference-optimization
Reference implementation for DPO (Direct Preference Optimization)
vincezengqiang/FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
vincezengqiang/fastllm
纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行
vincezengqiang/Firefly
Firefly(流萤): 中文对话式大语言模型(全量微调+QLoRA)
vincezengqiang/flash-attention
Fast and memory-efficient exact attention
vincezengqiang/KwaiAgents
A generalized information-seeking agent system with Large Language Models (LLMs).
vincezengqiang/LLaMA-Efficient-Tuning
Fine-tuning LLaMA with PEFT (PT+SFT+RLHF with QLoRA) LLM开源数据集
vincezengqiang/llama-recipes
Examples and recipes for Llama 2 model
vincezengqiang/LLM-Agent-Survey
vincezengqiang/LLM-Tuning
Tuning LLMs with no tears💦, sharing LLM-tools with love❤️.
vincezengqiang/LLM4Rec-Awesome-Papers
A list of awesome papers and resources of recommender system on large language model (LLM).
vincezengqiang/LLMDataHub
A quick guide (especially) for trending instruction finetuning datasets
vincezengqiang/LLMTest_NeedleInAHaystack
Doing simple retrieval from LLM models at various context lengths to measure accuracy
vincezengqiang/lmdeploy
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
vincezengqiang/LMOps
General technology for enabling AI capabilities w/ LLMs and MLLMs
vincezengqiang/Long-Context
This repository contains code and tooling for the Abacus.AI LLM Context Expansion project. Also included are evaluation scripts and benchmark tasks that evaluate a model’s information retrieval capabilities with context expansion. We also include key experimental results and instructions for reproducing and building on them.
vincezengqiang/LongQLoRA
LongQLoRA: Extent Context Length of LLMs Efficiently
vincezengqiang/MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练、有监督微调、RLHF(奖励建模、强化学习训练)和DPO(直接偏好优化)。
vincezengqiang/MergeLM
Codebase for Merging Language Models
vincezengqiang/metaso-free-api
🚀 秘塔AI搜索逆向API白嫖测试【特长：超强检索超长输出】，支持高速流式输出、超强联网搜索（全网or学术以及简洁、深入、研究三种模式），零配置部署，多路token支持
vincezengqiang/OpenLLaMA2
A High-performance LLaMA2 RLHF framework
vincezengqiang/prompts-royale
Automatically create prompts and make them fight each other to know which is the best
vincezengqiang/qlora
QLoRA: Efficient Finetuning of Quantized LLMs
vincezengqiang/torch-cam
Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)
vincezengqiang/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs