muyu42 / DataSLinks
本项目旨在结合以往研究人员的代表性工作，从多个维度评估sft数据，并自动化过滤sft数据。
☆44Updated last year
Alternatives and similar repositories for DataS
Users that are interested in DataS are comparing it to the libraries listed below
Sorting:
- [EMNLP 2024 Findings] Official PyTorch Implementation of "Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Ge…☆39Updated 7 months ago
- High performance rank executor for advertisement and recommendation system, implemented in C/C++ and support ensembled into Java/Scala ho…☆76Updated last year
- ☆62Updated 10 months ago
- Invoke Interfaces Only When Needed: Adaptive Invocation for Large Language Models in Question Answering☆42Updated 4 months ago
- NLP自学仓库☆24Updated last year
- An open-source highly heterogeneous entity alignment (HHEA) toolkit.☆32Updated last year
- StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving☆21Updated 9 months ago
- Ein multimodaler, multi-intelligenter Entwicklungsrahmen☆44Updated 3 months ago
- WordGPT是一款可以结合个人知识库或联网查询资料快速生成高质量论文、简历、博客、新闻稿、产品描述、故事、邮件、剧本、诗歌、工作汇报，及思维导图、文章配图等内容，同时可以进行各种语言的翻译，还能根据文本生成PPT的的工具。☆51Updated last year
- 通过RPN with FPN以及CRNN进行车牌检测和识别☆26Updated 8 months ago
- 检索增强生成的核心逻辑，因关键技术保密，无法提供图向量的提取生成和检索逻辑☆32Updated 10 months ago
- [ICME 2024] Official Datasets and example of LLM-SAP: Large Language Model Situational Awareness Based Planning☆33Updated 5 months ago
- ☆26Updated last year
- 即迅语音识别服务，支持语音识别（ASR）、语音合成（TTS）、声纹识别（VPR）等功能，适配国产化arm操作系统，支持CPU快速语音识别☆74Updated last year
- This search engine leverages the Boost library for efficient document search, featuring data preprocessing, index creation, and advanced …☆57Updated last year
- 中/英文 拼音/字符 模糊匹配库☆37Updated last month
- ☆45Updated last year
- ☆36Updated last year
- 使用donut多模态模型，身份证识别，对身份证做端对端识别,无需中间处理，识别率达到商用☆18Updated last year
- MGCF-Net for Phishing URLs Detection☆51Updated 3 months ago
- mobile predict☆25Updated 9 months ago
- [COLING Demos 2025] an Easy-to-use Tool for Comprehensive Response Evaluation of LLMs☆37Updated 6 months ago
- LoRA fine-tuning Mistral-7b-v2 on PR Task☆19Updated last year
- ☆33Updated 2 years ago
- Training and evaluation code of EGTLM model.☆23Updated last year
- 📕 DDmkTCCorpus: Diachronic Danmaku Text Comments Corpus （历时弹幕语料库）☆15Updated last year
- This script monitors the remaining traffic of VMs on Vultr, DigitalOcean, and Linode. If the remaining traffic is zero, it shuts down the…☆33Updated last year
- Typeless Programming Language `sicpy` and Compiler;☆33Updated 2 years ago
- ☆43Updated 2 years ago
- A 3D game involves melee combat and parkour system based on UE5.☆28Updated last year