ethicalabs/Echo-SmolTools-114M-NSFW-CLF

Echo-SmolTools-114M-NSFW-CLF

     

[!WARNING] This repository contains experimental models designed strictly for academic evaluation and research purposes. Critical Constraints: No Production Deployment: Experimental models must not be deployed in commercial, enterprise, or mission-critical environments under any circumstances. No Liability: Experimental models are provided "as-is" without warranties of any kind. The developers assume zero liability for downstream consequences, system integration failures, or regulatory non-compliance resulting from unauthorized deployment.

Binary sequence classification model based on the Echo-DSRN architecture. Merged from the base model `ethicalabs/Echo-DSRN-114M-v0.1.2` and the PEFT adapter `ethicalabs/Echo-SmolTools-114M-NSFW-CLF-PEFT`.

The classification head is seeded from the lm_head token rows for the label tokens. The chat template used during training is baked into config.json and applied automatically by classify().

Model Details

• —Architecture: EchoForSequenceClassification
• —Base model: ethicalabs/Echo-DSRN-114M-v0.1.2
• —Adapter: ethicalabs/Echo-SmolTools-114M-NSFW-CLF-PEFT
• —Labels: {0: 'Safe', 1: 'NSFW'}
• —Dtype: bfloat16

Usage

This model requires trust_remote_code=True to load the custom architecture.

import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification

model_id = "ethicalabs/Echo-SmolTools-114M-NSFW-CLF"  # or your hub path

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForSequenceClassification.from_pretrained(
    model_id,
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

label, probs = model.classify("Enter your text here", tokenizer)
print(f"Prediction: {label}")