https://github.com/thunlp/InfLLM

The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory"
https://github.com/thunlp/InfLLM

large-language-models llm long-context training-free

Last synced: 3 months ago
JSON representation

The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory"

• Host: GitHub
• URL: https://github.com/thunlp/InfLLM
• Owner: thunlp
• Created: 2024-03-03T01:27:49.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-03-24T04:40:05.000Z (4 months ago)
• Last Synced: 2024-03-24T07:24:27.446Z (4 months ago)
• Topics: large-language-models, llm, long-context, training-free
• Language: Python
• Homepage:
• Size: 243 KB
• Stars: 69
• Watchers: 10
• Forks: 5
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Lists

• awesome-stars - thunlp/InfLLM - The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory" (Python)
• awesome-stars - thunlp/InfLLM - The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory" (llm)
• StarryDivineSky - thunlp/InfLLM