Qianhui WU

qianhuiwu's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

New activity in microsoft/llmlingua-2 15 days ago

Fix error when force_tokens includes multi-word sequence to preserve

1

#2 opened about 1 month ago by cornzz

upvoted 2 papers 4 months ago

Wolf: Captioning Everything with a World Summarization Framework

Paper • 2407.18908 • Published Jul 26 • 31

MindSearch: Mimicking Human Minds Elicits Deep AI Searcher

Paper • 2407.20183 • Published Jul 29 • 38

upvoted 2 articles 4 months ago

view article

Article

MInference 1.0: 10x Faster Million Context Inference with a Single GPU

By •

Jul 11

• 11

view article

Article

How to Optimize TTFT of 8B LLMs with 1M Tokens to 20s

By •

Jul 21

• 2

upvoted a paper 5 months ago

MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention

Paper • 2407.02490 • Published Jul 2 • 23

liked a Space 5 months ago

Running on Zero

58

🌍

MInference

authored a paper 5 months ago

MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention

Paper • 2407.02490 • Published Jul 2 • 23

New activity in microsoft/llmlingua-2-xlm-roberta-large-meetingbank 5 months ago

Context length for compression

1

#2 opened 6 months ago by Money123001

How is the Inference API implemented

1

#3 opened 6 months ago by cnafan

liked 3 Spaces 6 months ago

Running

153

🔥

EasyOCR

Running

177

⚡

Remove Photo Object

Sleeping

357

📚

Grounded Segment Anything

updated 2 datasets 6 months ago

microsoft/MeetingBank-LLMCompressed

Viewer • Updated May 16 • 5.17k • 91 • 14

microsoft/MeetingBank-QA-Summary

Viewer • Updated May 16 • 862 • 158 • 11

liked 2 models 7 months ago

microsoft/llmlingua-2-xlm-roberta-large-meetingbank

Token Classification • Updated Apr 3 • 24.8k • 15

microsoft/llmlingua-2-bert-base-multilingual-cased-meetingbank

Token Classification • Updated Apr 3 • 34.4k • 21

updated 2 models 8 months ago

microsoft/llmlingua-2-xlm-roberta-large-meetingbank

Token Classification • Updated Apr 3 • 24.8k • 15

microsoft/llmlingua-2-bert-base-multilingual-cased-meetingbank

Token Classification • Updated Apr 3 • 34.4k • 21

Reacted to iofu728's post with ❤️ 8 months ago

view post

Post

1426

Reply

Welcome to LLMLingua-2, a small-size yet powerful prompt compression method trained via data distillation from GPT-4 for token classification with a BERT-level encoder, excels in task-agnostic compression. It surpasses LLMLingua in handling out-of-domain data, offering 3x-6x faster performance. @qianhuiwu

website: https://llmlingua.com/llmlingua2.html
code: https://github.com/microsoft/LLMLingua
demo: microsoft/llmlingua-2

• 
• 
• 2 replies

·

🔥

7

7

❤️

1

1

+