Pinned Repositories
absa-llm-augmentation
absa_llm
active-prompt
Source code for the paper "Active Prompting with Chain-of-Thought for Large Language Models"
agents
An Open-source Framework for Autonomous Language Agents
AgentVerse
🤖 AgentVerse 🪐 provides a flexible framework that simplifies the process of building custom multi-agent environments for large language models (LLMs).
ai-app
本项目旨在分享人工智能相关应用技术以及实战经验，包括大模型、语音合成、数字人、图像生成等。
ChatGPT-Next-Web
One-Click to deploy well-designed ChatGPT web UI on Vercel. 一键拥有你自己的 ChatGPT 网页服务。
extract_news_elements
JittorLLMs
计图大模型推理库，具有高性能、配置要求低、中文支持好、可移植等特点
wiseflow
wiseflow（首席情报官）是一个完备的领域（行业）开源信息情报获取与管理系统，用户既可以针对已有信源自行编写专有爬虫，使用本系统进行完备的流程管理，甚至一键生成报告，同时也可以订阅我们专业的信息情报服务。
RayJue's Repositories
RayJue/autodistill-gpt-4o
GPT-4o (with Vision) module for use with Autodistill.
RayJue/baby-llama2-chinese
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
RayJue/BitDistiller
[ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.
RayJue/CCL2024-CFSP-LLM
RayJue/ChatTTS
ChatTTS is a generative speech model for daily dialogue.
RayJue/data_serialize
RayJue/finetune_DistilBert_using_LORA
RayJue/flowgen
AutoGen Visualized - Visual Tools for Multi-Agent Development.
RayJue/FunClip
Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.
RayJue/G-LLaVA
Official github repo of G-LLaVA
RayJue/GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
RayJue/ImagesAnnotation
Image annotation tool using LLaVA
RayJue/LLaVA-Med
Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.
RayJue/LLM-Data-Cleaner
用大模型批量处理数据，现支持各种大模型做OCR，支持通义千问, 月之暗面, 百度飞桨OCR, OpenAI 和LLAVA。Use LLM to generate or clean data for academic use. Support OCR with qwen, moonshot, PaddleOCR, OpenAI, Llava.
RayJue/LLM_Tree_Search
(ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training
RayJue/meet-libai
李白 :bust_in_silhouette: 作为唐代杰出诗人，其诗歌作品在**文学史上具有重要地位。近年来，随着数字技术和人工智能的快速发展，传统文化普及推广的形式也面临着创新与变革。国内外对于李白诗歌的研究虽已相当深入，但在数字化、智能化普及方面仍存在不足。因此，本项目旨在通过构建李白知识图谱，结合大模型训练出专业的AI智能体，以生成式对话应用的形式，推动李白文化的普及与推广。
RayJue/Megatron-LLM
distributed trainer for LLMs
RayJue/MemGPT
Create LLM agents with long-term memory and custom tools 📚🦙
RayJue/MetaIE
This is a meta-model distilled from LLMs for information extraction. This is an intermediate checkpoint that can be well-transferred to all kinds of downstream information extraction tasks.
RayJue/MOELoRA-peft
[SIGIR'24] The official implementation code of MOELoRA.
RayJue/Multimodal-Table-Understanding
Dataset and Code for our ACL 2024 paper: "Multimodal Table Understanding". We propose the first large-scale Multimodal IFT and PT Dataset for table understanding and develop a generalist tabular MLLM Table-LLaVA.
RayJue/OfflineRL
A collection of offline reinforcement learning algorithms.
RayJue/Omost
Your image is almost there!
RayJue/OpenDevin
🐚 OpenDevin: Code Less, Make More
RayJue/PoSE
Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)
RayJue/rag-experiment-accelerator
The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.
RayJue/retrieve_and_rank
This repository implements a movie recommendation system using TensorFlow Recommenders (TFRS) with the MovieLens 100K dataset. It features retrieval and ranking models employing a two-tower architecture for user and movie embeddings, and demonstrates a brute-force search method for candidate retrieval.
RayJue/TinyLLaVA_Factory
A Framework of Small-scale Large Multimodal Models
RayJue/Video-ChatGPT
[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.
RayJue/wine-label-recognizer
Wine Label Recognizer: Extract wine name, vintage, producer from label images using OpenAI's GPT-4o API.