Svalabs
Rank:Average Model Cost: $0.0000
Number of Runs: 4,951
Models by this creator
gbert-large-zeroshot-nli
$-/run
2.1K
Huggingface
twitter-xlm-roberta-crypto-spam
twitter-xlm-roberta-crypto-spam
Platform did not provide a description for this model.
$-/run
1.1K
Huggingface
ger-roberta
$-/run
722
Huggingface
infoxlm-german-question-answering
infoxlm-german-question-answering
Platform did not provide a description for this model.
$-/run
477
Huggingface
cross-electra-ms-marco-german-uncased
$-/run
290
Huggingface
bi-electra-ms-marco-german-uncased
bi-electra-ms-marco-german-uncased
Platform did not provide a description for this model.
$-/run
156
Huggingface
rembert-german-question-answering
rembert-german-question-answering
Platform did not provide a description for this model.
$-/run
49
Huggingface
twitter-xlm-roberta-bitcoin-sentiment
twitter-xlm-roberta-bitcoin-sentiment
This model is mainly focussed on extracting the sentiment on tweets regarding bitcoin. The model was trained on manually on labeled data with rubrix (https://www.rubrix.ml/). The training set approximately contained 500 samples and 500 test samples. The cardiffnlp/twitter-xlm-roberta-base-sentiment (https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-sentiment) was used as weak classifier and also as base-model for finetuning.
$-/run
43
Huggingface
mt5-large-german-query-gen-v1
mt5-large-german-query-gen-v1
svalabs/mt5-large-german-query-gen-v1 This is a german doc2query model usable for document expansion to further boost search results by generating queries. Usage (code from doc2query/msmarco-14langs-mt5-base-v1) Console Output: References 'Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks'. 'MS MARCO: A Human Generated MAchine Reading COmprehension Dataset'. 'GermanQuAD and GermanDPR: Improving Non-English Question Answering and Passage Retrieval'. google/mt5-large mMARCO dataset doc2query
$-/run
41
Huggingface
german-gpl-adapted-covid
german-gpl-adapted-covid
svalabs/german-gpl-adapted-covid This is a german on covid adapted sentence-transformers model: It is adapted on covid related documents using the GPL integration of Haystack. We used the svalabs/cross-electra-ms-marco-german-uncased as CrossEncoder and svalabs/mt5-large-german-query-gen-v1 for query generation. Usage (Sentence-Transformers) Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: Evaluation Results Training The model was trained with the parameters: DataLoader: torch.utils.data.dataloader.DataLoader of length 125 with parameters: Loss: sentence_transformers.losses.MarginMSELoss.MarginMSELoss Parameters of the fit()-Method: Full Model Architecture Citing & Authors
$-/run
17
Huggingface