Navteca
Rank:Average Model Cost: $0.0000
Number of Runs: 20,234
Models by this creator
ms-marco-MiniLM-L-6-v2
ms-marco-MiniLM-L-6-v2
The ms-marco-MiniLM-L-6-v2 model is a pre-trained Cross-Encoder that can be used for Information Retrieval tasks, such as ranking passages based on a given query. It was trained on the MS Marco Passage Ranking task and can be used with SentenceTransformers. The model's performance on the TREC Deep Learning 2019 and MS Marco Passage Reranking datasets is provided. Runtime for the model was computed on a V100 GPU.
$-/run
17.1K
Huggingface
nli-deberta-v3-xsmall
$-/run
1.7K
Huggingface
multi-qa-mpnet-base-cos-v1
multi-qa-mpnet-base-cos-v1
Multi QA MPNet base model for Semantic Search This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and was designed for semantic search. It has been trained on 215M (question, answer) pairs from diverse sources. This model uses mpnet-base. Training Data We use the concatenation from multiple datasets to fine-tune this model. In total we have about 215M (question, answer) pairs. The model was trained with MultipleNegativesRankingLoss using Mean-pooling, cosine-similarity as similarity function, and a scale of 20. Technical Details In the following some technical details how this model must be used: Note: This model produces normalized embeddings with length 1. In that case, dot-product and cosine-similarity are equivalent. dot-product is preferred as it is faster. Euclidean distance is proportional to dot-product and can also be used. Usage and Performance The trained model can be used like this:
$-/run
670
Huggingface
deberta-v3-large-squad2
deberta-v3-large-squad2
Deberta v3 large model for QA (SQuAD 2.0) This is the deberta-v3-large model, fine-tuned using the SQuAD2.0 dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Question Answering. Training Data The models have been trained on the SQuAD 2.0 dataset. It can be used for question answering task. Usage and Performance The trained model can be used like this: Author deepset
$-/run
297
Huggingface
bart-large-mnli
bart-large-mnli
Bart large model for NLI-based Zero Shot Text Classification This model uses bart-large. Training Data This model was trained on the MultiNLI (MNLI) dataset in the manner originally described in Yin et al. 2019. It can be used to predict whether a topic label can be assigned to a given sequence, whether or not the label has been seen before. Usage and Performance The trained model can be used like this:
$-/run
255
Huggingface
deberta-v3-base-squad2
$-/run
75
Huggingface
nli-deberta-v3-large
nli-deberta-v3-large
Cross-Encoder for Natural Language Inference This model was trained using SentenceTransformers Cross-Encoder class. This model is based on microsoft/deberta-v3-large Training Data The model was trained on the SNLI and MultiNLI datasets. For a given sentence pair, it will output three scores corresponding to the labels: contradiction, entailment, neutral. Performance Accuracy on SNLI-test dataset: 92.20 Accuracy on MNLI mismatched set: 90.49 For futher evaluation results, see SBERT.net - Pretrained Cross-Encoder. Usage Pre-trained models can be used like this: Usage with Transformers AutoModel You can use the model also directly with Transformers library (without SentenceTransformers library): Zero-Shot Classification This model can also be used for zero-shot-classification:
$-/run
65
Huggingface
tapas-large-finetuned-wtq
tapas-large-finetuned-wtq
TAPAS large model fine-tuned on WikiTable Questions (WTQ) TAPAS is a BERT-like transformers model pretrained on a large corpus of English data from Wikipedia in a self-supervised fashion. This means it was pretrained on the raw tables and associated texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was pretrained with two objectives: Masked language modeling (MLM): taking a (flattened) table and associated context, the model randomly masks 15% of the words in the input, then runs the entire (partially masked) sequence through the model. The model then has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of a table and associated text. Intermediate pre-training: to encourage numerical reasoning on tables, the authors additionally pre-trained the model by creating a balanced dataset of millions of syntactically created training examples. Here, the model must predict (classify) whether a sentence is supported or refuted by the contents of a table. The training examples are created based on synthetic as well as counterfactual statements. This way, the model learns an inner representation of the English language used in tables and associated texts, which can then be used to extract features useful for downstream tasks such as answering questions about a table, or determining whether a sentence is entailed or refuted by the contents of a table. TAPAS: Weakly Supervised Table Parsing via Pre-training Training Data This model was pre-trained on MLM and an additional step which the authors call intermediate pre-training, and then fine-tuned in a chain on SQA, WikiSQL and finally WTQ. It can be used for answering questions related to a table. Usage and Performance The trained model can be used like this:
$-/run
60
Huggingface
electra-base-squad2
$-/run
23
Huggingface
roberta-base-squad2
roberta-base-squad2
Roberta base model for QA (SQuAD 2.0) This model uses roberta-base. Training Data The models have been trained on the SQuAD 2.0 dataset. It can be used for question answering task. Usage and Performance The trained model can be used like this:
$-/run
23
Huggingface