Feature Extraction
Transformers
Safetensors
English
bert
tinybert
authorship-verification
contrastive-learning
cosine-similarity
pan2020
pan2021
Eval Results (legacy)
text-embeddings-inference
Instructions to use peterkirby/tinybert-pan2020-authorship-verification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use peterkirby/tinybert-pan2020-authorship-verification with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="peterkirby/tinybert-pan2020-authorship-verification")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("peterkirby/tinybert-pan2020-authorship-verification") model = AutoModel.from_pretrained("peterkirby/tinybert-pan2020-authorship-verification", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_hyperparameters.json from peterkirby/tinybert-pan2020-authorship-verification: direct link, hf CLI and curl.
- Browser
- Download file 587 Bytes
-
https://huggingface.co/peterkirby/tinybert-pan2020-authorship-verification/resolve/main/training_hyperparameters.json
- Command line
-
hf download hf://peterkirby/tinybert-pan2020-authorship-verification/training_hyperparameters.json
-
curl -L -o training_hyperparameters.json https://huggingface.co/peterkirby/tinybert-pan2020-authorship-verification/resolve/main/training_hyperparameters.json
587 Bytes
| { | |
| "model_config": { | |
| "model_name_or_path": "huawei-noah/TinyBERT_General_4L_312D", | |
| "attn_implementation": "flash_attention_2", | |
| "pooling": "mean", | |
| "head_type": "none", | |
| "normalize": true | |
| }, | |
| "loss_dict": { | |
| "name": "supcon", | |
| "loss_config": { | |
| "temperature": 0.01 | |
| }, | |
| "loss_optim_config": {} | |
| }, | |
| "lr": 0.0004, | |
| "head_lr_multiplier": 5.0, | |
| "weight_decay": 0.01, | |
| "beta1": 0.9, | |
| "beta2": 0.999, | |
| "eps": 1e-08, | |
| "lr_schedule": "linear", | |
| "warmup_ratio": 0.1, | |
| "compile": true, | |
| "microbatch_size": 256, | |
| "cross_batch_memory_size": null | |
| } | |