---
library_name: transformers
tags:
- chunking
- RAG
license: mit
datasets:
- bookcorpus/bookcorpus
language:
- en
base_model:
- distilbert/distilbert-base-uncased
---

# Chonky distilbert base (uncased) v1

__Chonky__ is a transformer model that intelligently segments text into meaningful semantic chunks. This model can be used in the RAG systems.



## Model Description

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


## How to use

I've made a small python library for this model: [chonky](https://github.com/mirth/chonky)

Here is the usage:

```
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("--")
```

But you can use this model using standart 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}
]

```

## Training Data

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


## Metrics

| Metric   | Value |
| -------- | ------|
| F1       | 0.7   |
| Precision| 0.79  |
| Recall   | 0.63  |
| Accuracy | 0.99  |

## Hardware

Model was fine-tuned on 2x1080ti


I dedicate this model in memory of my father.