Downloads · 30 days
8
30% of all-time downloads
NanoBERT-V1
alan-yahya/NanoBERT-V1
NanoBERT-V1 is a machine learning model from alan-yahya. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This model is further pre-trained from google-bert/bert-base-uncased using a corpus consisting of 200,000 Nanoscience and Nanotechnology papers.
All-time downloads
27
Public
Parameters
133M
266 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors266 MB · 99%
At a glance
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Nov 19, 2024
- Updated
- Nov 19, 2024
- SHA
- 1d8fce05
Base models
Datasets
Model card
From the Hugging Face model README
NanoBERT-V1
This model is further pre-trained from google-bert/bert-base-uncased using a corpus consisting of 200,000 Nanoscience and Nanotechnology papers.
For practical applications, please use https://huggingface.co/Flamenco43/NanoBERT-V2
Intended uses & limitations
Intended for training on downstream tasks using Nanoscience datasets. Can be used directly to create dense vector representations for information retrieval.
Training and evaluation data
Trained using 2 nodes on Polaris: https://docs.alcf.anl.gov/polaris/hardware-overview/machine-overview/
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 256
- total_eval_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000000
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0
- Datasets 2.20.0
- Tokenizers 0.19.1
- Type
- bert
- License
- apache-2.0
- Created
- Nov 19, 2024
- Updated
- Nov 19, 2024