Update README.md

README.md

@@ -1,199 +1,137 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- chunking
+- RAG
+license: mit
+datasets:
+- bookcorpus/bookcorpus
+- JeanKaddour/minipile
+language:
+- en
+base_model:
+- answerdotai/ModernBERT-large
 ---
 
-# Model Card for Model ID
+# Chonky modernbert large v1
 
-<!-- Provide a quick summary of what the model is/does. -->
+__Chonky__ is a transformer model that intelligently segments text into meaningful semantic chunks. This model can be used in the RAG systems.
 
 
 
-## Model Details
+## Model Description
 
-### 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.
 
-<!-- Provide a longer summary of what this model is. -->
+⚠️This model was fine-tuned on sequence of length 1024 (by default ModernBERT supports sequence length up to 8192).
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+## How to use
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+I've made a small python library for this model: [chonky](https://github.com/mirth/chonky)
 
-### Model Sources [optional]
+Here is the usage:
 
-<!-- Provide the basic links for the model. -->
+```
+from chonky import TextSplitter
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+# on the first run it will download the transformer model
+splitter = TextSplitter(
+  model_id="mirth/chonky_modernbert_large_1",
+  device="cpu"
+)
 
-## Uses
+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."""
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+for chunk in splitter(text):
+  print(chunk)
+  print("--")
+```
 
-### Direct Use
+### Sample Output
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+```
+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.
+--
+```
 
-[More Information Needed]
+But you can use this model using standart NER pipeline:
 
-### Downstream Use [optional]
+```
+from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+model_name = "mirth/chonky_modernbert_large_1"
 
-[More Information Needed]
+tokenizer = AutoTokenizer.from_pretrained(model_name, model_max_length=1024)
 
-### Out-of-Scope Use
+id2label = {
+    0: "O",
+    1: "separator",
+}
+label2id = {
+    "O": 0,
+    "separator": 1,
+}
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+model = AutoModelForTokenClassification.from_pretrained(
+    model_name,
+    num_labels=2,
+    id2label=id2label,
+    label2id=label2id,
+)
 
-[More Information Needed]
 
-## Bias, Risks, and Limitations
+pipe = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy="simple")
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+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."""
 
-[More Information Needed]
+pipe(text)
 
-### Recommendations
+```
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+### Sample Output
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+```
 
-## How to Get Started with the Model
+[
+  {'entity_group': 'separator', 'score': np.float32(0.91590524), 'word': ' stories.', 'start': 209, 'end': 218},
+  {'entity_group': 'separator', 'score': np.float32(0.6210419), 'word': ' processing."', 'start': 455, 'end': 468},
+  {'entity_group': 'separator', 'score': np.float32(0.7071036), 'word': '.', 'start': 652, 'end': 653}
+]
+```
 
-Use the code below to get started with the model.
+## Training Data
 
-[More Information Needed]
+The model was trained to split paragraphs from minipile and bookcorpus datasets.
 
-## Training Details
 
-### Training Data
+## Metrics
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+Token based metrics for minipile:
 
-[More Information Needed]
+| Metric   | Value |
+| -------- | ------|
+| F1       | 0.85  |
+| Precision| 0.87  |
+| Recall   | 0.82  |
+| Accuracy | 0.99  |
 
-### Training Procedure
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+Token based metrics for bookcorpus:
 
-#### Preprocessing [optional]
+| Metric   | Value |
+| -------- | ------|
+| F1       | 0.79  |
+| Precision| 0.85  |
+| Recall   | 0.74  |
+| Accuracy | 0.99  |
 
-[More Information Needed]
 
+## Hardware
 
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+Model was fine-tuned on a single H100 for a several hours