-
Fudan University
- Shanghai
Highlights
- Pro
Stars
Open source codebase powering the HuggingChat app
Let your Claude able to think
ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)
O1 Replication Journey: A Strategic Progress Report – Part I
V2rayU,基于v2ray核心的mac版客户端,用于科学上网,使用swift编写,支持trojan,vmess,shadowsocks,socks5等服务协议,支持订阅, 支持二维码,剪贴板导入,手动配置,二维码分享等
[ACL2024] T-Eval: Evaluating Tool Utilization Capability of Large Language Models Step by Step
[KDD'2024] "HiGPT: Heterogenous Graph Language Models"
Learning to Compress Prompts with Gist Tokens - https://arxiv.org/abs/2304.08467
BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
RAFT, or Retrieval-Augmented Fine-Tuning, is a method comprising of a fine-tuning and a RAG-based retrieval phase. It is particularly suited for the creation of agents that realistically emulate a …
A unified evaluation framework for large language models
Open Academic Research on Improving LLaMA to SOTA LLM
[ACL 2024] An Easy-to-use Instruction Processing Framework for LLMs.
KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents
④[ECCV 2024 Oral, Comparison among Multiple Images!] A study on open-ended multi-image quality comparison: a dataset, a model and a benchmark.
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
What's In My Big Data (WIMBD) - a toolkit for analyzing large text datasets
A Python library to perform NER on structured data and generate PII with Faker
This package features data-science related tasks for developing new recognizers for Presidio. It is used for the evaluation of the entire system, as well as for evaluating specific PII recognizers …
Application and python script to identify, remove, and/or recode personally identifiable information (PII) from field experiment datasets.
EarlyBird is a sensitive data detection tool capable of scanning source code repositories for clear text password violations, PII, outdated cryptography methods, key files and more.