OFA-Sys/ExpertLLaMA
An opensource ChatBot built with ExpertPrompting which achieves 96% of ChatGPT's capability.
Uses "ExpertPrompting"—a technique that prepends dynamically-generated expert identity descriptions to instructions—to augment 52k Alpaca instruction-following examples generated by GPT-3.5, enabling the 7B LLaMA base model to achieve near-parity with ChatGPT responses. Trained using standard supervised fine-tuning on expert-augmented data without specialized prompt engineering, accessible via HuggingFace model hub and live demo space.
302 stars. No commits in the last 6 months.
Stars
302
Forks
20
Language
Python
License
Apache-2.0
Category
Last pushed
May 31, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/OFA-Sys/ExpertLLaMA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jakobdylanc/llmcord
Make Discord your LLM frontend - Supports any OpenAI compatible API (Ollama, xAI, Gemini,...
xNul/chat-llama-discord-bot
A Discord Bot for chatting with LLaMA, Vicuna, Alpaca, MPT, or any other Large Language Model...
amanvirparhar/weebo
A real-time speech-to-speech chatbot powered by Whisper Small, Llama 3.2, and Kokoro-82M.
ma2za/telegram-llm-bot
Telegram LLM bot backed by OpenAI, Whisper, Beam, LLaMA, Weaviate, MinIO and MongoDB
innightwolfsleep/old_llm_telegram_bot
Connect llama-cpp, transformers or text-generation-webui to telegram bot api.