Skip to content

models roberta base openai detector

Jump to bottom
github-actions[bot] edited this page Jan 4, 2024 · 23 revisions

roberta-base-openai-detector

Overview

RoBERTa Base OpenAI Detector is a language model developed by OpenAI that is fine-tuned using outputs from the 1.5B GPT-2 model. It is designed to detect text generated by GPT-2 and is not meant to be used for malicious purposes or to evade detection. The main focus of the model is to aid in synthetic text generation research, but users should be aware of its limitations, risks and potential biases, including accuracy and robustness limitations and the possibility of bias and stereotypes. The associated paper provides information on the training procedure and results from testing, which showed that the model achieved approximately 95% accuracy in detecting text generated by GPT-2, with a higher accuracy when trained using nucleus sampling. Further improvement to the model's effectiveness is said to require methods such as metadata-based approaches, human judgment, and public education.

The above summary was generated using ChatGPT. Review the original model card to understand the data used to train the model, evaluation metrics, license, intended uses, limitations and bias before using the model.

Inference samples

Inference type Python sample (Notebook) CLI with YAML
Real time text-classification-online-endpoint.ipynb text-classification-online-endpoint.sh
Batch entailment-contradiction-batch.ipynb coming soon

Finetuning samples

Task Use case Dataset Python sample (Notebook) CLI with YAML
Text Classification Emotion Detection Emotion emotion-detection.ipynb emotion-detection.sh
Token Classification Named Entity Recognition Conll2003 named-entity-recognition.ipynb named-entity-recognition.sh
Question Answering Extractive Q&A SQUAD (Wikipedia) extractive-qa.ipynb extractive-qa.sh

Model Evaluation

Task Use case Dataset Python sample (Notebook) CLI with YAML
Text Classification Detecting GPT2 Output GPT2-Outputs evaluate-model-text-classification.ipynb evaluate-model-text-classification.yml

Sample inputs and outputs (for real-time inference)

Sample input

{
    "input_data": {
        "input_string": ["Today was an amazing day!", "It was an unfortunate series of events."]
    }
}

Sample output

[
    {
        "0": "Fake"
    },
    {
        "0": "Fake"
    }
]

Version: 12

Tags

license : mit task : text-classification SharedComputeCapacityEnabled training_datasets : bookcorpus, wikipedia huggingface_model_id : roberta-base-openai-detector evaluation_compute_allow_list : ['Standard_DS4_v2', 'Standard_D8a_v4', 'Standard_D8as_v4', 'Standard_DS5_v2', 'Standard_D16a_v4', 'Standard_D16as_v4', 'Standard_D32a_v4', 'Standard_D32as_v4', 'Standard_D48a_v4', 'Standard_D48as_v4', 'Standard_D64a_v4', 'Standard_D64as_v4', 'Standard_D96a_v4', 'Standard_D96as_v4', 'Standard_F4s_v2', 'Standard_FX4mds', 'Standard_F8s_v2', 'Standard_FX12mds', 'Standard_F16s_v2', 'Standard_F32s_v2', 'Standard_F48s_v2', 'Standard_F64s_v2', 'Standard_F72s_v2', 'Standard_FX24mds', 'Standard_FX36mds', 'Standard_FX48mds', 'Standard_E2s_v3', 'Standard_E4s_v3', 'Standard_E8s_v3', 'Standard_E16s_v3', 'Standard_E32s_v3', 'Standard_E48s_v3', 'Standard_E64s_v3', 'Standard_NC4as_T4_v3', 'Standard_NC6s_v3', 'Standard_NC8as_T4_v3', 'Standard_NC12s_v3', 'Standard_NC16as_T4_v3', 'Standard_NC24s_v3', 'Standard_NC64as_T4_v3', 'Standard_NC24ads_A100_v4', 'Standard_NC48ads_A100_v4', 'Standard_NC96ads_A100_v4', 'Standard_ND96asr_v4', 'Standard_ND96amsr_A100_v4', 'Standard_ND40rs_v2'] finetune_compute_allow_list : ['Standard_NC12s_v3', 'Standard_NC24s_v3', 'Standard_NC24rs_v3', 'Standard_ND40rs_v2', 'Standard_ND96amsr_A100_v4', 'Standard_ND96asr_v4'] inference_compute_allow_list : ['Standard_DS3_v2', 'Standard_D4a_v4', 'Standard_D4as_v4', 'Standard_DS4_v2', 'Standard_D8a_v4', 'Standard_D8as_v4', 'Standard_DS5_v2', 'Standard_D16a_v4', 'Standard_D16as_v4', 'Standard_D32a_v4', 'Standard_D32as_v4', 'Standard_D48a_v4', 'Standard_D48as_v4', 'Standard_D64a_v4', 'Standard_D64as_v4', 'Standard_D96a_v4', 'Standard_D96as_v4', 'Standard_F4s_v2', 'Standard_FX4mds', 'Standard_F8s_v2', 'Standard_FX12mds', 'Standard_F16s_v2', 'Standard_F32s_v2', 'Standard_F48s_v2', 'Standard_F64s_v2', 'Standard_F72s_v2', 'Standard_FX24mds', 'Standard_FX36mds', 'Standard_FX48mds', 'Standard_E2s_v3', 'Standard_E4s_v3', 'Standard_E8s_v3', 'Standard_E16s_v3', 'Standard_E32s_v3', 'Standard_E48s_v3', 'Standard_E64s_v3', 'Standard_NC4as_T4_v3', 'Standard_NC6s_v3', 'Standard_NC8as_T4_v3', 'Standard_NC12s_v3', 'Standard_NC16as_T4_v3', 'Standard_NC24s_v3', 'Standard_NC64as_T4_v3', 'Standard_NC24ads_A100_v4', 'Standard_NC48ads_A100_v4', 'Standard_NC96ads_A100_v4', 'Standard_ND96asr_v4', 'Standard_ND96amsr_A100_v4', 'Standard_ND40rs_v2'] model_specific_defaults : ordereddict({'apply_deepspeed': 'true', 'apply_lora': 'true', 'apply_ort': 'true'})

View in Studio: https://ml.azure.com/registries/azureml/models/roberta-base-openai-detector/version/12

License: mit

Properties

SharedComputeCapacityEnabled: True

SHA: f5444000d615d1366ab9432a981035c58c57d55f

evaluation-min-sku-spec: 8|0|28|56

inference-min-sku-spec: 4|0|14|28

finetune-min-sku-spec: 12|2|224|1474

evaluation-recommended-sku: Standard_DS4_v2, Standard_D8a_v4, Standard_D8as_v4, Standard_DS5_v2, Standard_D16a_v4, Standard_D16as_v4, Standard_D32a_v4, Standard_D32as_v4, Standard_D48a_v4, Standard_D48as_v4, Standard_D64a_v4, Standard_D64as_v4, Standard_D96a_v4, Standard_D96as_v4, Standard_F4s_v2, Standard_FX4mds, Standard_F8s_v2, Standard_FX12mds, Standard_F16s_v2, Standard_F32s_v2, Standard_F48s_v2, Standard_F64s_v2, Standard_F72s_v2, Standard_FX24mds, Standard_FX36mds, Standard_FX48mds, Standard_E2s_v3, Standard_E4s_v3, Standard_E8s_v3, Standard_E16s_v3, Standard_E32s_v3, Standard_E48s_v3, Standard_E64s_v3, Standard_NC4as_T4_v3, Standard_NC6s_v3, Standard_NC8as_T4_v3, Standard_NC12s_v3, Standard_NC16as_T4_v3, Standard_NC24s_v3, Standard_NC64as_T4_v3, Standard_NC24ads_A100_v4, Standard_NC48ads_A100_v4, Standard_NC96ads_A100_v4, Standard_ND96asr_v4, Standard_ND96amsr_A100_v4, Standard_ND40rs_v2

inference-recommended-sku: Standard_DS3_v2, Standard_D4a_v4, Standard_D4as_v4, Standard_DS4_v2, Standard_D8a_v4, Standard_D8as_v4, Standard_DS5_v2, Standard_D16a_v4, Standard_D16as_v4, Standard_D32a_v4, Standard_D32as_v4, Standard_D48a_v4, Standard_D48as_v4, Standard_D64a_v4, Standard_D64as_v4, Standard_D96a_v4, Standard_D96as_v4, Standard_F4s_v2, Standard_FX4mds, Standard_F8s_v2, Standard_FX12mds, Standard_F16s_v2, Standard_F32s_v2, Standard_F48s_v2, Standard_F64s_v2, Standard_F72s_v2, Standard_FX24mds, Standard_FX36mds, Standard_FX48mds, Standard_E2s_v3, Standard_E4s_v3, Standard_E8s_v3, Standard_E16s_v3, Standard_E32s_v3, Standard_E48s_v3, Standard_E64s_v3, Standard_NC4as_T4_v3, Standard_NC6s_v3, Standard_NC8as_T4_v3, Standard_NC12s_v3, Standard_NC16as_T4_v3, Standard_NC24s_v3, Standard_NC64as_T4_v3, Standard_NC24ads_A100_v4, Standard_NC48ads_A100_v4, Standard_NC96ads_A100_v4, Standard_ND96asr_v4, Standard_ND96amsr_A100_v4, Standard_ND40rs_v2

finetune-recommended-sku: Standard_NC12s_v3, Standard_NC24s_v3, Standard_NC24rs_v3, Standard_ND40rs_v2, Standard_ND96amsr_A100_v4, Standard_ND96asr_v4

finetuning-tasks: text-classification, token-classification, question-answering

languages: en

Wiki menu

Clone this wiki locally