zp940328
Follow
Stars
AIGC-interview/CV-interview/LLMs-interview面试问题与答案集合仓，同时包含工作和科研过程中的新想法、新问题、新资源与新项目
一个可以验证和计算文本消耗 Token 的小工具，支持在浏览器中使用，汉化自 OpenAI Tokenizer。
🦜🔗 Build context-aware reasoning applications
【LLMs九层妖塔】分享 LLMs在自然语言处理（ChatGLM、Chinese-LLaMA-Alpaca、小羊驼 Vicuna、LLaMA、GPT4ALL等）、信息检索（langchain）、语言合成、语言识别、多模态等领域（Stable Diffusion、MiniGPT-4、VisualGLM-6B、Ziya-Visual等）等 实战与经验。
360LayoutAnaylsis, a series Document Analysis Models and Datasets deleveped by 360 AI Research Institute
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…
🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. 基于中文法律知识的大语言模型
HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance
总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力
Doctor Dignity is an LLM that can pass the US Medical Licensing Exam. It works offline, it's cross-platform, & your health data stays private.
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
MobiLlama : Small Language Model tailored for edge devices
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Code and documentation to train Stanford's Alpaca models, and generate the data.
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.
micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-…
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
Open deep learning compiler stack for cpu, gpu and specialized accelerators
A Gradio web UI for Large Language Models with support for multiple inference backends.
聚宝盆(Cornucopia): 中文金融系列开源可商用大模型，并提供一套高效轻量化的垂直领域LLM训练框架(Pretraining、SFT、RLHF、Quantize等)
中文法律LLaMA (LLaMA for Chinese legel domain)
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)