0hq / WebGPT
Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.
☆3,687Updated last year
Alternatives and similar repositories for WebGPT:
Users that are interested in WebGPT are comparing it to the libraries listed below
- Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.☆3,646Updated last year
- An LLM playground you can run on your laptop☆6,340Updated 2 months ago
- Build LLM apps in Typescript/Javascript. 🧑💻 🧑💻 🧑💻 🚀 🚀 🚀☆1,762Updated 2 years ago
- Secure open source cloud runtime for AI apps & AI agents☆7,798Updated this week
- An LLM-powered autonomous agent platform☆1,388Updated last month
- LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath☆9,358Updated 7 months ago
- Automate your browser with GPT-4☆1,167Updated 2 months ago
- Let ChatGPT teach your own chatbot in hours with a single GPU!☆3,171Updated last year
- Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)☆11,909Updated this week
- Plugins for Auto-GPT☆3,882Updated 10 months ago
- StableLM: Stability AI Language Models☆15,836Updated 11 months ago
- Get a ChatGPT plugin up and running in under 5 minutes!☆4,237Updated last year
- gpt4all-j chat☆1,266Updated last year
- the first library to let you embed a developer agent in your own app!☆11,901Updated 11 months ago
- A school for camelids☆1,208Updated last year
- bloop is a fast code search engine written in Rust.☆9,468Updated 3 months ago
- RAG on Paul Graham's essays.☆2,660Updated last year
- OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset☆7,462Updated last year
- Locally run an Instruction-Tuned Chat-Style LLM☆10,237Updated last year
- Turbopilot is an open source large-language-model based code completion engine that runs locally on CPU☆3,821Updated last year
- An AutoGPT agent that controls Chrome on your desktop☆1,724Updated last year
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,043Updated 6 months ago
- High-performance In-browser LLM Inference Engine☆15,031Updated 2 months ago
- Agent techniques to augment your LLM and push it beyong its limits☆1,570Updated 9 months ago
- The simplest way to run LLaMA on your local machine☆13,083Updated 9 months ago
- The no-code platform for building custom LLM Agents☆2,931Updated 9 months ago
- CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.☆5,050Updated last month
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,278Updated 4 months ago
- Drive a browser with GPT-3☆1,919Updated 9 months ago
- AI companions with memory: a lightweight stack to create and host your own AI companions☆5,814Updated 10 months ago