en
AI Ranking
每月不到10元,就可以无限制地访问最好的AIbase。立即成为会员
Home
News
Daily Brief
Income Guide
Tutorial
Tools Directory
Product Library
en
AI Ranking
Search AI Products and News
Explore worldwide AI information, discover new AI opportunities
AI News
AI Tools
AI Cases
AI Tutorial
Type :
AI News
AI Tools
AI Cases
AI Tutorial
2023-10-23 16:44:52
.
AIbase
.
2.4k
Tsinghua's Latest Research Significantly Enhances Llama2's General Intelligence Capabilities, Approaching GPT-4 Levels
Tsinghua University's latest research introduces the AgentTuning method to enhance LLM's agent capabilities. The AgentInstruct agent dataset has been constructed, containing high-quality interactive trajectories and CoT reasoning chains. A hybrid instruction fine-tuning strategy was adopted, using AgentInstruct in conjunction with general instructions. Results indicate that AgentLM outperforms Llama 2 significantly in both held-in and held-out tasks. The 70B version of AgentLM excels in agent tasks.