jiezhangGt
Follow
Stars
Tools for merging pretrained large language models.
Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
【CVPR 2024 Highlight】Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]
Netease Youdao's open-source embedding and reranker models for RAG products.
🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.
A Gradio web UI for Large Language Models.
Create LLM agents with long-term memory and custom tools 📚🦙
AgentTuning: Enabling Generalized Agent Abilities for LLMs
🩹Editing large language models within 10 seconds⚡
Ongoing research training transformer language models at scale, including: BERT & GPT-2
GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
Fast and memory-efficient exact attention
simple crawler for some uyghur website such as uy.ts.cn,bbs.bagdax.cn,www.bagdax.cn(using python and scrapy)
纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.
⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.
Easily share permanent links to ChatGPT conversations with your friends
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.