Highlights
- Pro
Stars
A repo for open resources & information for people to succeed in PhD in CS & career in AI / NLP
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
Recent papers on (1) Psychology of LLMs; (2) Biases in LLMs.
🤫 Code and benchmark for our ICLR 2024 spotlight paper: "Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory"
[ACL 2024 Findings] "TempCompass: Do Video LLMs Really Understand Videos?", Yuanxin Liu, Shicheng Li, Yi Liu, Yuxiang Wang, Shuhuai Ren, Lei Li, Sishuo Chen, Xu Sun, Lu Hou
This repo is the code and synthetic data of the ACM MM 2024 paper "SCREEN: A Benchmark for Situated Conversational Recommendation"
Repo for paper "Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents"
Repository containing standard ML algorithms that might be asked in Machine Learning Coding Interviews
This is the official repository for HypoGeniC (Hypothesis Generation in Context), which is an automated, data-driven tool that leverages large language models to generate hypothesis for open-domain…
Implementation for paper: The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models
An AI-chat bot transforming counseling with personalized support and expert assistance.
Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (ACL 2024)
Official code for ICML 2024 paper on Persona In-Context Learning (PICLe)
ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
Label Studio is a multi-type data labeling and annotation tool with standardized output format
A programming framework for agentic AI 🤖
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
PATIENT-Ψ: Using Large Language Models to Simulate Patients for Training Mental Health Professionals
Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline!
整理 pytorch 单机多 GPU 训练方法与原理
SimPO: Simple Preference Optimization with a Reference-Free Reward
Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"