Optimum

Rank:

Average Model Cost: $0.0000

Number of Runs: 140,477

Models by this creator

t5-small

T5-small is an encoder-decoder model that has been pre-trained on a variety of unsupervised and supervised tasks. It is designed to convert various natural language processing tasks into a text-to-text format. The model has been trained with transfer learning and can be used for a variety of translation tasks.

$-/run

70.1K

Huggingface

sbert-all-MiniLM-L6-with-pooler

optimum

No description available.

$-/run

25.7K

Huggingface

distilbert-base-uncased-finetuned-sst-2-english

optimum

The distilbert-base-uncased-finetuned-sst-2-english model is a fine-tuned version of the DistilBERT-base-uncased model. It has been trained on the sentiment analysis task SST-2 and achieves an accuracy of 91.3% on the dev set. The model uses a learning rate of 1e-5, a batch size of 32, a warmup of 600 steps, a maximum sequence length of 128, and is trained for 3 epochs. It is important to note that this model may produce biased predictions, particularly for underrepresented populations. It is recommended to thoroughly evaluate the model's performance and biases in specific use cases.

$-/run

22.2K

Huggingface

gpt2

optimum

GPT-2 is a pretrained language model that was trained on a large corpus of English text data using a self-supervised learning approach. It was trained to predict the next word in sentences and can generate text given a prompt. The model can be used for text generation or can be fine-tuned for specific downstream tasks. It has been released as an ONNX model and can be used with the transformers library.

$-/run

21.0K

Huggingface

tiny_random_bert_neuron

optimum