Model Trained Using AutoNLP

  • Problem type: Extractive Question Answering
  • Model ID: 26265898
  • CO2 Emissions (in grams): 82.78379967029494

Validation Metrics

  • Loss: 0.5732079148292542

Usage

You can use cURL to access this model:

$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"question": "Who loves AutoNLP?", "context": "Everyone loves AutoNLP"}' https://api-inference.huggingface.co/models/teacookies/autonlp-more_fine_tune_24465520-26265898

Or Python API:

import torch

from transformers import AutoModelForQuestionAnswering, AutoTokenizer

model = AutoModelForQuestionAnswering.from_pretrained("teacookies/autonlp-more_fine_tune_24465520-26265898", use_auth_token=True)

tokenizer = AutoTokenizer.from_pretrained("teacookies/autonlp-more_fine_tune_24465520-26265898", use_auth_token=True)

from transformers import BertTokenizer, BertForQuestionAnswering

question, text = "Who loves AutoNLP?", "Everyone loves AutoNLP"

inputs = tokenizer(question, text, return_tensors='pt')

start_positions = torch.tensor([1])

end_positions = torch.tensor([3])

outputs = model(**inputs, start_positions=start_positions, end_positions=end_positions)

loss = outputs.loss

start_scores = outputs.start_logits

end_scores = outputs.end_logits
Downloads last month
9
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.