Downloads · 30 days
10
32% of all-time downloads
pneumatix-id-2024
Tenta42/pneumatix-id-2024
pneumatix-id-2024 is a question answering model from Tenta42. Use it when the input is a question plus a passage. It is set up for transformers.
- Problem type: Extractive Question Answering
All-time downloads
31
Public
Parameters
336M
8.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt5.4 GB · 57%
At a glance
- Task
- Question Answering
- Library
- transformers
- Model type
- camembert
- Access
- Public
- Created
- Mar 16, 2025
- Updated
- Mar 16, 2025
- SHA
- 62f66f1f
Try a prompt
Base models
Model card
From the Hugging Face model README
Model Trained Using AutoTrain
- Problem type: Extractive Question Answering
Validation Metrics
loss: 0.061212386935949326
exact_match: 95.3771
f1: 95.384
runtime: 64.0039
samples_per_second: 150.303
steps_per_second: 4.703
: 5.0
Usage
import torch
from transformers import AutoModelForQuestionAnswering, AutoTokenizer
model = AutoModelForQuestionAnswering.from_pretrained(...)
tokenizer = AutoTokenizer.from_pretrained(...)
from transformers import BertTokenizer, BertForQuestionAnswering
question, text = "Who loves AutoTrain?", "Everyone loves AutoTrain"
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
- Task
- Question Answering
- Library
- transformers
- Type
- camembert
- Created
- Mar 16, 2025
- Updated
- Mar 16, 2025