models t5 base

t5-base

Overview

T5 Base is a text-to-text transformer model that can be used for a variety of NLP tasks, such as machine translation, document summarization, question answering and classification tasks, such as sentiment analysis. It was developed by a team at Google and is pre-trained on the Colossal Clean Crawled Corpus. It is licensed under Apache 2.0 and you can start using the model by installing the T5 tokenizer and model and following the examples provided in the Colab Notebook created by its developers. Be mindful of bias, risks and limitations that may arise while using this model.

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	translation-online-endpoint.ipynb	translation-online-endpoint.sh
Batch	translation-batch-endpoint.ipynb	coming soon

Finetuning samples

Task	Use case	Dataset	Python sample (Notebook)	CLI with YAML
Summarization	News Summary	CNN DailyMail	news-summary.ipynb	news-summary.sh
Translation	Translate English to Romanian	WMT16	translate-english-to-romanian.ipynb	translate-english-to-romanian.sh

Model Evaluation

Task	Use case	Dataset	Python sample (Notebook)	CLI with YAML
Translation	Translation	wmt16/ro-en	evaluate-model-translation.ipynb	evaluate-model-translation.yml

Sample inputs and outputs (for real-time inference)

Sample input

{
    "input_data": {
        "input_string": ["My name is John and I live in Seattle", "Berlin is the capital of Germany."]
    },
    "parameters": {
        "task_type": "translation_en_to_fr"
    }
}

Sample output

[
    {
        "0": "Mon nom est John et je vivais à Seattle."
    },
    {
        "0": "Berlin est la capitale de l'Allemagne."
    }
]

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 : apache-2.0 model_specific_defaults : ordereddict([('apply_deepspeed', 'true'), ('apply_lora', 'true'), ('apply_ort', 'true')]) task : text-translation

View in Studio: https://ml.azure.com/registries/azureml/models/t5-base/version/11

License: apache-2.0

Properties

SHA: 0db7e623bcaee2daf9b859a646637ea39bf016cd

datasets: c4

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_NC24rs_v3

finetuning-tasks: summarization, translation

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

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_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_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, fr, ro, de