诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

My Leetcode Solutions

Towards Robust Multimodal Sentiment Analysis with Incomplete Data

Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis (ALMT)

Test equality between a black-box LLM API and a reference distribution

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

总结Prompt&LLM论文，开源数据&模型，AIGC应用

Implements harmful/harmless refusal removal using pure HF Transformers

Integrate the DeepSeek API into popular softwares

Automated Safety Testing of Large Language Models

[ICSE'25] Aligning the Objective of LLM-based Program Repair

Medical o1, Towards medical complex reasoning with LLMs

Xiaomi Home Integration for Home Assistant

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning method which reduces LLM performance on WMDP while retaining …

Paper list for Personal LLM Agents

A Test Project for a Network Security-oriented LLM Tool Emulating AutoGPT

Create Custom LLMs

This project generates a high-quality Alpaca-style dataset from input text files, PDFs, and Word documents.

Code for the paper "PortraitNet: Real-time portrait segmentation network for mobile device" @ CAD&Graphics2019

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

A curation of awesome tools, documents and projects about LLM Security.

A toolkit to assess data privacy in LLMs (under development)