-
Notifications
You must be signed in to change notification settings - Fork 124
models t5 small
Description: T5 Small is a text-to-text transformer model with 60 million parameters. It is developed by a group of researchers and is based on the Text-To-Text Transfer Transformer (T5) framework, which allows for a unified text-to-text format for input and output of all NLP tasks. T5-Small can be trained for multiple NLP tasks such as machine translation, document summarization, question answering, classification, and even regression tasks. It is pre-trained on the Colossal Clean Crawled Corpus (C4) and a multi-task mixture of unsupervised and supervised tasks in various languages, such as English, French, Romanian and German. You can use the code provided to get started with the model and refer to the resources provided for more information on the 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 json { "inputs": { "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 json [ { "0": "Mon nom est John et je vivais à Seattle." }, { "0": "Berlin est la capitale de l'Allemagne." } ]
Version: 9
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-small/version/9
License: apache-2.0
SHA: 3479082dc36f8a4730936ef1c9b88cd8b0835c53
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: 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, fr, ro, de