kobigbird-pure2-36745331
alphahg
Pregunta y respuesta
Este modelo es una versión afinada de monologg/kobigbird-bert-base en el conjunto de datos custom_squad_v2. Logra los siguientes resultados en el conjunto de evaluación: Pérdida: 1.4250
Como usar
Los siguientes hiperparámetros se utilizaron durante el entrenamiento:
learning_rate: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 2
gradient_accumulation_steps: 8
total_train_batch_size: 256
optimizer: Adam con betas=(0.9,0.999) y epsilon=1e-08
lr_scheduler_type: cosine
num_epochs: 2
mixed_precision_training: Native AMP
Transformers 4.25.1
Pytorch 1.13.1
Datasets 2.8.0
Tokenizers 0.13.2
Ejemplos de uso del modelo
Where do I live?
Contexto: My name is Wolfgang and I live in Berlin
Where do I live?
Contexto: My name is Sarah and I live in London
What's my name?
Contexto: My name is Clara and I live in Berkeley.
Which name is also used to describe the Amazon rainforest in English?
Contexto: The Amazon rainforest (Portuguese: Floresta Amazônica or Amazônia; Spanish: Selva Amazónica, Amazonía or usually Amazonia; French: Forêt amazonienne; Dutch: Amazoneregenwoud), also known in English as Amazonia or the Amazon Jungle, is a moist broadleaf forest that covers most of the Amazon basin of South America. This basin encompasses 7,000,000 square kilometres (2,700,000 sq mi), of which 5,500,000 square kilometres (2,100,000 sq mi) are covered by the rainforest. This region includes territory belonging to nine nations. The majority of the forest is contained within Brazil, with 60% of the rainforest, followed by Peru with 13%, Colombia with 10%, and with minor amounts in Venezuela, Ecuador, Bolivia, Guyana, Suriname and French Guiana. States or departments in four nations contain "Amazonas" in their names. The Amazon represents over half of the planet's remaining rainforests, and comprises the largest and most biodiverse tract of tropical rainforest in the world, with an estimated 390 billion individual trees divided into 16,000 species.
Funcionalidades
- Alineado a partir de monologg/kobigbird-bert-base
- Utiliza el conjunto de datos custom_squad_v2
- Compatible con endpoints de inferencia
- Utiliza el marco Transformers 4.25.1
- Entrenado con PyTorch 1.13.1
Casos de uso
- Responder preguntas basadas en un contexto dado
- Desarrollar aplicaciones de asistencia de preguntas y respuestas automatizadas
- Emplear en sistemas interactivos de educación y e-learning