microsoft / token-classification updated 1 year ago

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

Name: llmlingua-2-bert-base-multilingual-cased-meetingbank
Author: microsoft

This model was introduced in the paper LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression (Pan et al, 2024). It is a BERT multilingual base model (cased) finetuned to perform token classification for task agnostic prompt compression. The probability $p{preserve}$ of each token $xi$ is used as the metric for compression. This model is trained on the extractive text compression d...

Params

180 M

Context

512

Downloads 30d

493 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

493 K445 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	0.7 GB	1.3 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: BertForTokenClassification
Parameters: 180 M
Tensor type: F32
Context length: 512
Vocabulary: 119,647
Layers / heads: 12 / 12
Licence: apache-2.0
First seen on the Hub: 2024-03-17
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

indonesian-roberta-base-posp-tagger 3.1 M stanford-deidentifier-base 1.9 M bert-base-NER 1.3 M punctuate-all 708 K sat-3l-sm 558 K ner-english-fast 543 K

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB