🚀 ⭐ GLiClass：用於序列分類的通用輕量級模型
GLiClass 是一個高效的零樣本分類器，受 GLiNER 工作的啟發而開發。它在分類性能上與交叉編碼器相當，但計算效率更高，因為它只需一次前向傳播即可完成分類。
該模型可用於 主題分類、情感分析，還能在 RAG 管道中作為重排器使用。模型基於合成數據和可商用的許可數據進行訓練，因此可應用於商業場景。其骨幹模型為 mdeberta-v3-base，支持多語言理解，非常適合處理不同語言的文本任務。
🚀 快速開始
安裝 GLiClass 庫
首先，你需要安裝 GLiClass 庫：
pip install gliclass
pip install -U transformers>=4.48.0
初始化模型和管道
以下是不同語言的使用示例：
英語
from gliclass import GLiClassModel, ZeroShotClassificationPipeline
from transformers import AutoTokenizer
model = GLiClassModel.from_pretrained("knowledgator/gliclass-x-base")
tokenizer = AutoTokenizer.from_pretrained("knowledgator/gliclass-x-base", add_prefix_space=True)
pipeline = ZeroShotClassificationPipeline(model, tokenizer, classification_type='multi-label', device='cuda:0')
text = "One day I will see the world!"
labels = ["travel", "dreams", "sport", "science", "politics"]
results = pipeline(text, labels, threshold=0.5)[0]
for result in results:
print(result["label"], "=>", result["score"])
西班牙語
from gliclass import GLiClassModel, ZeroShotClassificationPipeline
from transformers import AutoTokenizer
model = GLiClassModel.from_pretrained("knowledgator/gliclass-x-base")
tokenizer = AutoTokenizer.from_pretrained("knowledgator/gliclass-x-base", add_prefix_space=True)
pipeline = ZeroShotClassificationPipeline(model, tokenizer, classification_type='multi-label', device='cuda:0')
text = "¡Un día veré el mundo!"
labels = ["viajes", "sueños", "deportes", "ciencia", "política"]
results = pipeline(text, labels, threshold=0.5)[0]
for result in results:
print(result["label"], "=>", result["score"])
意大利語
from gliclass import GLiClassModel, ZeroShotClassificationPipeline
from transformers import AutoTokenizer
model = GLiClassModel.from_pretrained("knowledgator/gliclass-x-base")
tokenizer = AutoTokenizer.from_pretrained("knowledgator/gliclass-x-base", add_prefix_space=True)
pipeline = ZeroShotClassificationPipeline(model, tokenizer, classification_type='multi-label', device='cuda:0')
text = "Un giorno vedrò il mondo!"
labels = ["viaggi", "sogni", "sport", "scienza", "politica"]
results = pipeline(text, labels, threshold=0.5)[0]
for result in results:
print(result["label"], "=>", result["score"])
法語
from gliclass import GLiClassModel, ZeroShotClassificationPipeline
from transformers import AutoTokenizer
model = GLiClassModel.from_pretrained("knowledgator/gliclass-x-base")
tokenizer = AutoTokenizer.from_pretrained("knowledgator/gliclass-x-base", add_prefix_space=True)
pipeline = ZeroShotClassificationPipeline(model, tokenizer, classification_type='multi-label', device='cuda:0')
text = "Un jour, je verrai le monde!"
labels = ["voyage", "rêves", "sport", "science", "politique"]
results = pipeline(text, labels, threshold=0.5)[0]
for result in results:
print(result["label"], "=>", result["score"])
德語
from gliclass import GLiClassModel, ZeroShotClassificationPipeline
from transformers import AutoTokenizer
model = GLiClassModel.from_pretrained("knowledgator/gliclass-x-base")
tokenizer = AutoTokenizer.from_pretrained("knowledgator/gliclass-x-base", add_prefix_space=True)
pipeline = ZeroShotClassificationPipeline(model, tokenizer, classification_type='multi-label', device='cuda:0')
text = "Eines Tages werde ich die Welt sehen!"
labels = ["Reisen", "Träume", "Sport", "Wissenschaft", "Politik"]
results = pipeline(text, labels, threshold=0.5)[0]
for result in results:
print(result["label"], "=>", result["score"])
📊 基準測試
以下是該模型在幾個文本分類數據集上的 F1 分數。所有測試模型均未在這些數據集上進行微調，而是在零樣本設置下進行測試。
多語言基準測試
| 數據集 |
gliclass-x-base |
gliclass-base-v3.0 |
gliclass-large-v3.0 |
| FredZhang7/toxi-text-3M |
0.5972 |
0.5072 |
0.6118 |
| SetFit/xglue_nc |
0.5014 |
0.5348 |
0.5378 |
| Davlan/sib200_14classes |
0.4663 |
0.2867 |
0.3173 |
| uhhlt/GermEval2017 |
0.3999 |
0.4010 |
0.4299 |
| dolfsai/toxic_es |
0.1250 |
0.1399 |
0.1412 |
| 平均 |
0.41796 |
0.37392 |
0.4076 |
通用基準測試
| 數據集 |
gliclass-x-base |
gliclass-base-v3.0 |
gliclass-large-v3.0 |
| SetFit/CR |
0.8630 |
0.9127 |
0.9398 |
| SetFit/sst2 |
0.8554 |
0.8959 |
0.9192 |
| SetFit/sst5 |
0.3287 |
0.3376 |
0.4606 |
| AmazonScience/massive |
0.2611 |
0.5040 |
0.5649 |
| stanfordnlp/imdb |
0.8840 |
0.9251 |
0.9366 |
| SetFit/20_newsgroups |
0.4116 |
0.4759 |
0.5958 |
| SetFit/enron_spam |
0.5929 |
0.6760 |
0.7584 |
| PolyAI/banking77 |
0.3098 |
0.4698 |
0.5574 |
| takala/financial_phrasebank |
0.7851 |
0.8971 |
0.9000 |
| ag_news |
0.6815 |
0.7279 |
0.7181 |
| dair-ai/emotion |
0.3667 |
0.4447 |
0.4506 |
| MoritzLaurer/cap_sotu |
0.3935 |
0.4614 |
0.4589 |
| cornell/rotten_tomatoes |
0.7252 |
0.7943 |
0.8411 |
| 平均 |
0.5737 |
0.6556 |
0.7001 |
📄 許可證
本項目採用 Apache-2.0 許可證。
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Transformers 支持多種語言