models roberta base openai detector

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: 11

Tags

Preview computes_allow_list : ['Standard_NV12s_v3', 'Standard_NV24s_v3', 'Standard_NV48s_v3', 'Standard_NC6s_v3', 'Standard_NC12s_v3', 'Standard_NC24s_v3', 'Standard_NC24rs_v3', 'Standard_NC6s_v2', 'Standard_NC12s_v2', 'Standard_NC24s_v2', 'Standard_NC24rs_v2', 'Standard_NC4as_T4_v3', 'Standard_NC8as_T4_v3', 'Standard_NC16as_T4_v3', 'Standard_NC64as_T4_v3', 'Standard_ND6s', 'Standard_ND12s', 'Standard_ND24s', 'Standard_ND24rs', 'Standard_ND40rs_v2', 'Standard_ND96asr_v4'] license : mit model_specific_defaults : ordereddict({'apply_deepspeed': 'true', 'apply_lora': 'true', 'apply_ort': 'true'}) SharedComputeCapacityEnabled task : text-classification

View in Studio: https://ml.azure.com/registries/azureml/models/roberta-base-openai-detector/version/11

License: mit

Properties

SHA: f5444000d615d1366ab9432a981035c58c57d55f

datasets: bookcorpus, wikipedia

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

evaluation-recommended-sku: Standard_DS4_v2

finetune-min-sku-spec: 4|1|28|176

finetune-recommended-sku: Standard_NC12s_v3

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

inference-min-sku-spec: 2|0|7|14

inference-recommended-sku: Standard_DS2_v2, Standard_D2a_v4, Standard_D2as_v4, 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

languages: en