Downloads · 30 days
10
3% of all-time downloads
hier-bert-i3-mlm-v0.1
igorktech/hier-bert-i3-mlm-v0.1
hier-bert-i3-mlm-v0.1 is a fill-mask model from igorktech. Use it when you need the model to fill a missing word. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
371
Public
Repo size
575 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin143 MB · 98%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- hierarchical-bert
- Access
- Public
- Created
- Sep 24, 2023
- Updated
- Oct 9, 2023
- SHA
- 56772814
Try a prompt
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
hier-bert-i3-mlm
This model is a fine-tuned version of /content/hier-bert-pytorch/data/hier-model on an unknown dataset.
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: 0.001
- train_batch_size: 64
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.5
- training_steps: 5000
Training results
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
- Task
- Fill-Mask
- Library
- transformers
- Type
- hierarchical-bert
- Created
- Sep 24, 2023
- Updated
- Oct 9, 2023