Stars
Official PyTorch code for Deep Audio-Signal Holistic Embeddings
LongMIT: Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets
基于大模型搭建的聊天机器人，同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入，可选择GPT3.5/GPT-4o/GPT-o1/ Claude/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Claude/Kimi/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。
[ICASSP 2024] A BiRGAT Model for Multi-intent Spoken Language Understanding with Hierarchical Semantic Frames
MultilingualSIFT: Multilingual Supervised Instruction Fine-tuning
An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)
Summarize existing representative LLMs text datasets.
VideoSys: An easy and efficient system for video generation
Modeling, training, eval, and inference code for OLMo
Data and tools for generating and inspecting OLMo pre-training data.
DISC-LawLLM, an intelligent legal system utilizing large language models (LLMs) to provide a wide range of legal services
[ICLR 2024] Lemur: Open Foundation Models for Language Agents
The RedPajama-Data repository contains code for preparing large datasets for training large language models.
We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts…
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)
A guidance language for controlling large language models.
Easily train a good VC model with voice data <= 10 mins!
Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation me…
A cross-platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。