Instructions to use mahima18/qat5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mahima18/qat5 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("mahima18/qat5") model = AutoModelForSeq2SeqLM.from_pretrained("mahima18/qat5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Question Generation without Answers : End to End Generation
TrainingArguments
| Parameter | Value |
|---|---|
evaluation_strategy |
epoch |
learning_rate |
2e-5 |
per_device_train_batch_size |
8 |
per_device_eval_batch_size |
8 |
num_train_epochs |
3 |
weight_decay |
0.01 |
save_strategy |
epoch |
disable_tqdm |
False |
gradient_accumulation_steps |
2 |
Note : The batch size and acclumulation steps were decreased during training due to memory constraints.
Note : This model correcly predicts when called in the application but it is currently not giving correct questions in this inference api.
- Downloads last month
- 5
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support