8 5 6

Wenwei Zhang

ZwwWayne

AI & ML interests

None yet

Recent Activity

authored a paper 4 days ago

Are Your LLMs Capable of Stable Reasoning?

upvoted a paper 5 days ago

Are Your LLMs Capable of Stable Reasoning?

authored a paper 6 days ago

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

View all activity

Organizations

Posts 2

Post

1504

Here, we share the technical details of InternLM2, the current state-of-the-art open-source LLMs!!

See collections internlm/internlm2-65b0ce04970888799707893c
Paper: InternLM2 Technical Report (2403.17297)

Post

1714

How to let LLM acquire the Agentic Capability?

Previous answers are direct imitation learning by collecting agentic data such as tool calling history (inefficient and introduces format hallucination).
Agent-FLAN tells a different view:
- Eliciting the foundational capability (e.g., reasoning, retrieval, and instruction following) is more important
- Using chat data is more effective with less side effects than tool calling history

Dataset: internlm/Agent-FLAN
HF Model: internlm/Agent-FLAN-7b
Paper: Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models (2403.12881)
Project page：https://internlm.github.io/Agent-FLAN/

Papers 10

models

None public yet

datasets

None public yet