How to use from the
Use from the
Transformers library
# Use a pipeline as a high-level helper
# Warning: Pipeline type "question-answering" is no longer supported in transformers v5.
# You must load the model directly (see below) or downgrade to v4.x with:
# pip install "transformers<5.0.0"
from transformers import pipeline

pipe = pipeline("question-answering", model="sashakttripathi/transformers-question-answer")
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForQuestionAnswering

tokenizer = AutoTokenizer.from_pretrained("sashakttripathi/transformers-question-answer")
model = AutoModelForQuestionAnswering.from_pretrained("sashakttripathi/transformers-question-answer", device_map="auto")
Quick Links

transformers-question-answer

This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 1.4951
  • Validation Loss: 1.1651
  • Epoch: 0

Model description

This is a sample transformer trained for question-answer use case. I have used a pre-trained BERT model and then finetuned it using the hugging-face transformer library.

Training hyperparameters

The following hyperparameters were used during training:

  • optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 5e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
  • training_precision: mixed_float16

Training results

Train Loss Validation Loss Epoch
1.4951 1.1651 0

Framework versions

  • Transformers 4.31.0
  • TensorFlow 2.11.0
  • Datasets 2.14.2
  • Tokenizers 0.13.3
Downloads last month
8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for sashakttripathi/transformers-question-answer

Finetuned
(346)
this model