大模型RLHF(ppo奖励模型)训练偏好数据排序助手
Sorts large model answers to generate preference data for reward model training
AI Chat ·
Assistants, model playgrounds and autonomous agents. 389 products, newest first.
Sorts large model answers to generate preference data for reward model training
AI Chat ·
Chat with PDF files in Google Bard or Gemini
AI Chat ·
AI chatbot tool supporting multiple platforms like WeChat, Douyin, and
AI Chat ·
AI assistant supporting multiple models for chat, writing, and art creation
AI Chat ·
A web platform supporting GeminiPro Vision, Cloudflare Workers AI, and ChatGPT
AI Chat ·