Chonky Distilbert Base Uncased 1

🚀 Chonky distilbert base (uncased) v1

Chonky is a transformer model that can intelligently segment text into meaningful semantic chunks. It can be used in RAG systems, offering a practical solution for text processing and retrieval.

✨ Features

• The model processes text and divides it into semantically coherent segments. These chunks can be fed into embedding - based retrieval systems or language models as part of a RAG pipeline.

📦 Installation

The README doesn't provide specific installation steps. However, you can use the model through the provided Python libraries. You may need to install dependencies like transformers and chonky.

💻 Usage Examples

Basic Usage

You can use the chonky library for easy text splitting:

from chonky import ParagraphSplitter

# on the first run it will download the transformer model
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("--")

Advanced Usage

You can also use the model with the standard NER pipeline:

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)

# Output

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

📚 Documentation

Training Data

The model was trained to split paragraphs from the bookcorpus dataset.

Metrics

Hardware

The model was fine - tuned on 2x1080ti.

📄 License

This project is licensed under the MIT license.