Chonky Distilbert Base Uncased 1

🚀 分塊式蒸餾伯特基礎模型（無大小寫區分）v1

分塊式蒸餾伯特基礎模型 是一個能夠智能地將文本分割成有意義語義塊的Transformer模型。該模型可用於檢索增強生成（RAG）系統。

🚀 快速開始

本模型可用於將文本處理並分割成語義連貫的片段。這些片段隨後可作為RAG流程的一部分，輸入到基於嵌入的檢索系統或語言模型中。

✨ 主要特性

• 智能地將文本分割成有意義的語義塊。
• 可應用於RAG系統。

📦 安裝指南

你可以使用作者開發的小型Python庫 chonky 來使用此模型。

💻 使用示例

基礎用法

from chonky import ParagraphSplitter

# 首次運行時會下載Transformer模型
splitter = ParagraphSplitter(device="cpu")

text = """Before college the two main things I worked on, outside of school, were writing and programming. I didn't write essays. I wrote what beginning writers were supposed to write then, and probably still are: short stories. My stories were awful. They had hardly any plot, just characters with strong feelings, which I imagined made them deep. The first programs I tried writing were on the IBM 1401 that our school district used for what was then called "data processing." This was in 9th grade, so I was 13 or 14. The school district's 1401 happened to be in the basement of our junior high school, and my friend Rich Draves and I got permission to use it. It was like a mini Bond villain's lair down there, with all these alien-looking machines — CPU, disk drives, printer, card reader — sitting up on a raised floor under bright fluorescent lights."""

for chunk in splitter(text):
  print(chunk)
  print("--")

高級用法

你也可以使用標準的命名實體識別（NER）流程來使用此模型：

from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline

model_name = "mirth/chonky_distilbert_uncased_1"

tokenizer = AutoTokenizer.from_pretrained(model_name)

id2label = {
    0: "O",
    1: "separator",
}
label2id = {
    "O": 0,
    "separator": 1,
}

model = AutoModelForTokenClassification.from_pretrained(
    model_name,
    num_labels=2,
    id2label=id2label,
    label2id=label2id,
)

pipe = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy="simple")

text = """Before college the two main things I worked on, outside of school, were writing and programming. I didn't write essays. I wrote what beginning writers were supposed to write then, and probably still are: short stories. My stories were awful. They had hardly any plot, just characters with strong feelings, which I imagined made them deep. The first programs I tried writing were on the IBM 1401 that our school district used for what was then called "data processing." This was in 9th grade, so I was 13 or 14. The school district's 1401 happened to be in the basement of our junior high school, and my friend Rich Draves and I got permission to use it. It was like a mini Bond villain's lair down there, with all these alien-looking machines — CPU, disk drives, printer, card reader — sitting up on a raised floor under bright fluorescent lights."""

pipe(text)

# 輸出

[
  {'entity_group': 'separator', 'score': 0.89515704, 'word': 'deep.', 'start': 333, 'end': 338},
  {'entity_group': 'separator', 'score': 0.61160326, 'word': '.', 'start': 652, 'end': 653}
]

📚 詳細文檔

訓練數據

該模型使用來自書籍語料庫（bookcorpus）數據集的段落進行訓練。

評估指標

硬件環境

該模型在2塊1080ti顯卡上進行了微調。

📄 許可證

本項目採用MIT許可證。

信息表格