Instructions to use VINAY-UMRETHE/tiny-refusal-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use VINAY-UMRETHE/tiny-refusal-classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="VINAY-UMRETHE/tiny-refusal-classifier")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("VINAY-UMRETHE/tiny-refusal-classifier") model = AutoModelForSequenceClassification.from_pretrained("VINAY-UMRETHE/tiny-refusal-classifier", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download README.md from VINAY-UMRETHE/tiny-refusal-classifier: direct link, hf CLI and curl.
- Browser
- Download file 2.57 kB
-
https://huggingface.co/VINAY-UMRETHE/tiny-refusal-classifier/resolve/main/README.md
- Command line
-
hf download hf://VINAY-UMRETHE/tiny-refusal-classifier/README.md
-
curl -L -o README.md https://huggingface.co/VINAY-UMRETHE/tiny-refusal-classifier/resolve/main/README.md
library_name: transformers
base_model:
- VINAY-UMRETHE/Refusal-Classifier
license: apache-2.0
pipeline_tag: text-classification
tags:
- tiny
- random
- test
- testing
Tiny Randomly Initialized
Base Model: VINAY-UMRETHE/Refusal-Classifier
Purpose
This is a tiny, randomly initialized model that has not been trained on any dataset, so do not use this model for any real refusal classification tasks. It is used for testing in the GitHub CI of p-e-w/heretic (implemented in feat: Generic BERT Classifier scorer plugin #500), similar to how the other reproduction tests use models from the tiny-random organization.
You can also use this model for debugging without loading the real models (e.g. VINAY-UMRETHE/Refusal-Classifier, VINAY-UMRETHE/Refusal-Classifier-V2, etc.), as they share the same architecture and configuration (ModernBERT).
How this model was created
from typing import cast
import torch
from transformers import (
AutoConfig,
AutoTokenizer,
ModernBertForSequenceClassification,
PreTrainedTokenizerBase,
set_seed,
)
source_model_id = "VINAY-UMRETHE/Refusal-Classifier"
save_folder = "tiny-refusal-classifier"
tokenizer = cast(
PreTrainedTokenizerBase,
AutoTokenizer.from_pretrained(source_model_id),
)
tokenizer.save_pretrained(save_folder)
config = AutoConfig.from_pretrained(source_model_id)
config.hidden_size = 32
config.intermediate_size = 128
config.num_attention_heads = 1
config.num_hidden_layers = 2
config.layer_types = config.layer_types[:2]
model = ModernBertForSequenceClassification(config)
# FP32, matching the source model's dtype.
# Expected: torch.float32
print(next(model.parameters()).dtype)
set_seed(75)
with torch.no_grad():
for name, parameter in sorted(model.named_parameters()):
torch.nn.init.normal_(parameter, 0, 0.5)
print(name, parameter.shape)
model.save_pretrained(save_folder)
# Upload:
# model.push_to_hub(repo_id="VINAY-UMRETHE/tiny-refusal-classifier")
# tokenizer.push_to_hub(repo_id="VINAY-UMRETHE/tiny-refusal-classifier")
License
Copyright © 2026 Vinay Umrethe.
This model is licensed under the Apache License 2.0 License.