Update README.md

README.md

@@ -1,13 +1,23 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- paraphraser
+license: mit
+pipeline_tag: summarization
 ---
 
 # Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
+[Paraphrasing evades detectors of AI-generated text,
+but retrieval is an effective defense](https://arxiv.org/pdf/2303.13408.pdf) proposed a strong discourse paraphraser known as DIPPER.
 
+DIPPER is a large model, built from [google/t5-efficient-xxl](https://huggingface.co/google/t5-efficient-xxl) and finetuned on 6.3M datapoints.
+I am proposing a lightweight, non-context equivalent for lower-cost usage.
 
+This model is built from [google/t5-large-nl32](https://huggingface.co/google/t5-efficient-large-nl32) and finetuned on 100,000 datapoints.
+Notably, the datapoints are all non-context. Refer to the original paper if you wish for further understanding on this topic.
+
+The dataset used to finetune this model is available here: [Dataset](https://huggingface.co/datasets/SamSJackson/kpar3-no-ctx)
 
 ## Model Details
 
@@ -17,185 +27,138 @@ tags: []
 
 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 
-- **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]
+- **Developed by:** Sam Jackson 
+- **Model type:** Sequence-to-Sequence Model
+- **Language(s) (NLP):** English
+- **License:** MIT
+- **Finetuned from model [optional]:** [google/t5-large-nl32](https://huggingface.co/google/t5-efficient-large-nl32)
 
 ### Model Sources [optional]
 
 <!-- Provide the basic links for the model. -->
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
+- **Repository:** [Original Github](https://github.com/martiansideofthemoon/ai-detection-paraphrases)
+- **Paper [optional]:** [Paraphrasing evades detectors of AI-generated text,
+but retrieval is an effective defense](https://arxiv.org/pdf/2303.13408.pdf)
 - **Demo [optional]:** [More Information Needed]
 
 ## Uses
 
 <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+The model is intended to be used for paraphrasing with notions of control.
+The dataset used encourages lexical (word) and order (paragraph structure) parameters, which control the degree of strength in paraphrasing.
 
-### Direct Use
+See the example code usage for a further understanding.
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+### Direct Use
 
-[More Information Needed]
+The model is entirely usable from the uploaded state. No further finetuning is required, although possible.
 
 ### Downstream Use [optional]
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
+This model was finetuned from a T5 checkpoint.
+It is possible to further finetune this model, if desired.
+If you plan for transfer learning, I would simply recommend starting from the initial checkpoint model: [google/t5-large-nl32](https://huggingface.co/google/t5-efficient-large-nl32).
 
 ### Recommendations
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+In terms of recommendation, if you have the capacity, I would recommend using the more powerful model: [DIPPER](https://github.com/martiansideofthemoon/ai-detection-paraphrases) 
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+Otherwise, this model is sufficiently strong. 
+It outperforms the sentence-based paraphraser [ChatGPT Paraphraser](https://huggingface.co/humarin/chatgpt_paraphraser_on_T5_base) when it comes to perplexity scores - when both models are compared using the facebook/opt-2.7b model.
 
 ## How to Get Started with the Model
 
 Use the code below to get started with the model.
 
-[More Information Needed]
-
 ## Training Details
 
 ### Training Data
 
-<!-- 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. -->
-
-[More Information Needed]
+As mentioned, the training data is here: [kpar3-no-ctx](https://huggingface.co/datasets/SamSJackson/kpar3-no-ctx)
+Pre-processing simply contains tokenisation through the google/t5-efficient-large-nl32 tokenizer.
 
-### Training Procedure 
+The data is classic paraphrase pairs. However, the first element in the pair has terms "lexical = x" and "order = y". 
+The values x and y are in the set {0, 20, 40, 60, 80, 100} and denote the strength with which the model should paraphrase.
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
+In particular, a sentence with "lexical = 0" should change as many words as possible, while maintaining the original meaning.
+Meanwhile, a sentence with "order = 0" should restructure the paragraph to the model's greatest extent.
 
+The dataset only contains parameter values in increments of 20. 
 
 #### 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 -->
+- **Training regime:**  <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+```python
+learning_rate = 1e-4
+bf16 = True
+num_train_epochs = 2
+auto_find_batch_size = True,
+generation_num_beams = 2,
+generation_max_length = 200
+```
 
 #### 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]
+Finetuning on 100,000 datapoints, this took around 14 GPU hours using a GTX 3090. 
 
-#### Metrics
+### Example Usage
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
-[More Information Needed]
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
-### Results
+tokenizer = AutoTokenizer.from_pretrained("google/t5-efficient-large-nl32")
 
-[More Information Needed]
+model = AutoModelForSeq2SeqLM.from_pretrained("SamSJackson/paraphrase-dipper-no-ctx")
+model = model.to(device)
 
-#### Summary
+text = "Each Wednesdsay, I take my dog for a walk in Central Park."
 
+lexical = 20
+order = 40
 
+prompt = f"lexical = {lexical}, order = {order} {text}"
 
-## Model Examination [optional]
+input_ids = tokenizer(
+    prompt,
+    return_tensors='pt',
+    padding="longest",
+    max_length=1000,
+    truncation=True,
+).to(device)
 
-<!-- Relevant interpretability work for the model goes here -->
+outputs = model.generate(
+    **input_ids,
+    top_p=0.75,
+    do_sample=True,
+    max_new_tokens=300,
+)
 
-[More Information Needed]
+response = tokenizer.batch_decode(outputs, skip_special_tokens=True)
+response = f"{' '.join(response)}"
 
-## 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]
+print(response)
+```
 
 ## 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]
+```
+@misc{krishna2023paraphrasing,
+      title={Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense}, 
+      author={Kalpesh Krishna and Yixiao Song and Marzena Karpinska and John Wieting and Mohit Iyyer},
+      year={2023},
+      eprint={2303.13408},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```
 
 ## Model Card Contact
 
-[More Information Needed]
-
-
+Contact me through huggingface if you have any questions.