Sshleifer
Rank:Average Model Cost: $0.0000
Number of Runs: 1,206,112
Models by this creator
distilbart-cnn-12-6
distilbart-cnn-12-6
The distilbart-cnn-12-6 model is a pre-trained language model that is specifically trained for text summarization tasks. It is based on the distillation of the BART model and the CNN/DailyMail dataset. The model takes in a piece of text and generates a concise summary of that text. It can be used to automate the process of summarizing news articles, blog posts, or any other textual content.
$-/run
731.9K
Huggingface
tiny-marian-en-de
tiny-marian-en-de
The tiny-marian-en-de model is a text-to-text generation model trained using the MarianMT framework. It is specifically designed for English to German translation tasks. The model is relatively small in size, making it more efficient to use compared to larger models. It can be used to generate translations for short texts or sentences from English to German.
$-/run
237.7K
Huggingface
tiny-gpt2
tiny-gpt2
tiny-gpt2 is a language model with a smaller size and fewer parameters compared to the original GPT-2 model. It is capable of generating human-like text and can be used for tasks such as text completion, text generation, and dialogue systems. The smaller size of the model makes it more computationally efficient and allows it to be deployed on devices with limited resources.
$-/run
76.4K
Huggingface
tiny-distilroberta-base
tiny-distilroberta-base
The tiny-distilroberta-base model is a pre-trained language model that has been optimized for efficiency and low memory usage. It is based on the RoBERTa architecture and has been further distilled to reduce its size while maintaining good performance. This model can be used for various natural language processing tasks, such as text classification, named entity recognition, and language generation.
$-/run
55.7K
Huggingface
tiny-distilbert-base-cased-distilled-squad
tiny-distilbert-base-cased-distilled-squad
The tiny-distilbert-base-cased-distilled-squad model is a question-answering model that is based on the DistilBERT architecture. It is a smaller and more efficient version of the original BERT model, created by distilling knowledge from the larger BERT model into a smaller and faster model. The model has been fine-tuned on the SQuAD (Stanford Question Answering Dataset) task, which involves answering questions based on a given context passage. This model can be used to extract answers to questions from a given context passage.
$-/run
31.7K
Huggingface
tiny-mbart
tiny-mbart
The tiny-mbart model is a smaller version of the mBART model. It is designed for text-to-text generation tasks and has been trained on various multi-lingual datasets. The model can be fine-tuned on specific tasks and languages to generate high-quality outputs.
$-/run
27.8K
Huggingface
bart-tiny-random
bart-tiny-random
The bart-tiny-random model is a text generation model that is part of the BART architecture, which stands for Bidirectional and Auto-Regressive Transformer. The BART model is trained to understand and generate human-like text by predicting the next word or phrase given a sequence of input text. The bart-tiny-random variant is a smaller version of the BART model, designed to be more computationally efficient. It generates random output text based on the input provided.
$-/run
15.8K
Huggingface
tiny-dbmdz-bert-large-cased-finetuned-conll03-english
tiny-dbmdz-bert-large-cased-finetuned-conll03-english
The tiny-dbmdz-bert-large-cased-finetuned-conll03-english model is a fine-tuned version of the BERT (Bidirectional Encoder Representations from Transformers) model for named entity recognition (NER) on the CoNLL-2003 dataset. It is trained to identify and classify named entities such as persons, locations, organizations, and others in text. This model can be used to extract information from text and perform tasks such as information retrieval, question answering, and text summarization.
$-/run
12.7K
Huggingface
distilbart-cnn-6-6
distilbart-cnn-6-6
The distilbart-cnn-6-6 model is a language model trained for summarization tasks. It is based on the DistilBART architecture and is specifically fine-tuned for summarizing news articles. The model takes in an input text and generates a concise summary of the text. It has been trained on a large dataset of news articles and has the ability to understand and condense information effectively.
$-/run
9.5K
Huggingface
distilbart-xsum-12-6
distilbart-xsum-12-6
The distilbart-xsum-12-6 model is a pretrained model for text summarization. It is based on the BART architecture and is trained on the XSum dataset. The model can generate concise summaries of input text.
$-/run
7.1K
Huggingface