Ydshieh
Rank:Average Model Cost: $0.0000
Number of Runs: 9,987
Models by this creator
vit-gpt2-coco-en
vit-gpt2-coco-en
vit-gpt2-coco-en is a model that combines the Vision Transformer (ViT) architecture with the GPT-2 architecture to perform image-to-text tasks. It can generate textual descriptions of images when provided with visual inputs. The model is trained on the COCO (Common Objects in Context) dataset.
$-/run
5.3K
Huggingface
wav2vec2-large-xlsr-53-chinese-zh-cn-gpt
$-/run
2.6K
Huggingface
tiny-random-gptj-for-sequence-classification
tiny-random-gptj-for-sequence-classification
Platform did not provide a description for this model.
$-/run
485
Huggingface
bert-base-cased-squad2
$-/run
298
Huggingface
bert-base-uncased-yelp-polarity
bert-base-uncased-yelp-polarity
Platform did not provide a description for this model.
$-/run
286
Huggingface
roberta-base-squad2
$-/run
229
Huggingface
bert2bert-cnn_dailymail-fp16
$-/run
221
Huggingface
vit-gpt2-coco-en-ckpts
$-/run
213
Huggingface
roberta-large-ner-english
$-/run
190
Huggingface
clip-vit-base-patch32
$-/run
184
Huggingface