Downloads · 30 days
43
3% of all-time downloads
bloom560m-squad-helloworld
jasoneden/bloom560m-squad-helloworld
bloom560m-squad-helloworld is a question answering model from jasoneden. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as bigscience-bloom-rail-1.0.
This model is a fine-tuned version of bigscience/bloom-560m on the squadv2 dataset. It is intended for a proof of concept, and perhaps to serve as a starting point for others trying to do the same thing.
All-time downloads
1.7K
Public
Parameters
559M
4.5 GB on disk
Likes
8
Public
Repo makeup
Click a slice to open those files.
.bin4.5 GB · 67%
At a glance
- Task
- Question Answering
- Library
- transformers
- License
- bigscience-bloom-rail-1.0
- Model type
- bloom
- Access
- Public
- Created
- Oct 25, 2022
- Updated
- Sep 11, 2023
- SHA
- 89e92cd4
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has mostly been generated automatically according to the information the Trainer had access to. I've added some additional context. -->
POC - BLOOM for QuestionAnswering, tuned on squad_v2
This model is a fine-tuned version of bigscience/bloom-560m on the squad_v2 dataset. It is intended for a proof of concept, and perhaps to serve as a starting point for others trying to do the same thing.
Ongoing discussion surrounding this effort:
https://huggingface.co/bigscience/bloom/discussions/46#633c57b2ccce04161f82e6c2
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 6
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2.0
- mixed_precision_training: Native AMP
Training results
Framework versions
- Transformers 4.24.0.dev0
- Pytorch 1.12.1+cu102
- Datasets 2.6.1
- Tokenizers 0.13.1
- Task
- Question Answering
- Library
- transformers
- Type
- bloom
- License
- bigscience-bloom-rail-1.0
- Created
- Oct 25, 2022
- Updated
- Sep 11, 2023