🧠

Model

Pii Token Filter Hard Gretel

Name: Pii Token Filter Hard Gretel
Author: PuxAI

by PuxAI hf-model--puxai--pii-token-filter-hard-gretel

Free2AITools Nexus Index

37.9 Top 100%

S: Semantic 50

A: Authority 0

P: Popularity 3

R: Recency 92

Q: Quality 65

Tech Context

0.14B Params

512 Ctx

Vital Performance

31 DL / 30D

0.0%

Source →

Audited 37.9 FNI Score

Tiny 0.14B Params

1k Context

31 Downloads

8G GPU ~2GB Est. VRAM

Dense DEBERTAV2FORTOKENCLASSIFICATION Architecture

Commercial MIT License

Model Information Summary
Entity Passport
Registry ID	hf-model--puxai--pii-token-filter-hard-gretel
License	MIT
Provider	huggingface

💾

Compute Threshold

~1.4GB VRAM

Interactive

Analyze Hardware

Hardware Compatibility Test

▼

* Static estimation for 4-Bit Quantization.

📜

Cite this model

Academic & Research Attribution

BibTeX

@misc{hf_model__puxai__pii_token_filter_hard_gretel,
  author = {PuxAI},
  title = {Pii Token Filter Hard Gretel Model},
  year = {2026},
  howpublished = {\url{https://huggingface.co/PuxAI/PII-Token-Filter-Hard-gretel}},
  note = {Accessed via Free2AITools Knowledge Fortress}
}

APA Style

PuxAI. (2026). Pii Token Filter Hard Gretel [Model]. Free2AITools. https://huggingface.co/PuxAI/PII-Token-Filter-Hard-gretel

🔬Technical Deep Dive

Full Specifications [+]

Quick Commands

🦙 Ollama Run

ollama run pii-token-filter-hard-gretel

🤗 HF Download

huggingface-cli download puxai/pii-token-filter-hard-gretel

📦 Install Lib

pip install -U transformers

⚖️ Free2AITools Nexus Index V2.0

Methodology Index Protocol

Semantic (S) 50

Authority (A) 0

Popularity (P) 3

Recency (R) 92

Quality (Q) 65

💬 Index Insight

FNI V2.0 for Pii Token Filter Hard Gretel: Semantic (S:50), Authority (A:0), Popularity (P:3), Recency (R:92), Quality (Q:65).

Free2AITools Nexus Index

Verification Authority

HuggingFace API GitHub Metadata Arxiv Citation DB System Audit

Unbiased Data Node Refresh: VFS Live

---

🚀 What's Next?

📊

Find Training Datasets

Discover datasets compatible with this model

📈

Compare Benchmarks

See how this model ranks on standard tests

⚡

Deployment Guide

Understand deployment options

Technical Deep Dive

PII-Token-Filter-Hard-gretel

This model is a fine-tuned version of microsoft/deberta-v3-small on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1881
Precision: 0.5606
Recall: 0.5286
F1: 0.5441
Accuracy: 0.9297

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: 2e-05
train_batch_size: 16
eval_batch_size: 32
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	14	0.4122	0.1461	0.1857	0.1635	0.8421
No log	2.0	28	0.2819	0.472	0.4214	0.4453	0.8919
No log	3.0	42	0.2216	0.5546	0.4714	0.5097	0.9165
No log	4.0	56	0.1960	0.5814	0.5357	0.5576	0.9275
No log	5.0	70	0.1881	0.5606	0.5286	0.5441	0.9297

Framework versions

Transformers 4.56.0
Pytorch 2.8.0+cu129
Datasets 4.8.2
Tokenizers 0.22.0

⚠️ Incomplete Data

Some information about this model is not available. Use with Caution - Verify details from the original source before relying on this data.

View Original Source →

📝 Limitations & Considerations

• Benchmark scores may vary based on evaluation methodology and hardware configuration.
• VRAM requirements are estimates; actual usage depends on quantization and batch size.
• FNI scores are relative rankings and may change as new models are added.
⚠ License Unknown: Verify licensing terms before commercial use.

Social Proof

HuggingFace Hub

31Downloads

Hub Discussions

🤗 Data Source: Hugging Face ↗

🔄 Daily sync (03:00 UTC)

AI Summary: Based on Hugging Face metadata. Not a recommendation.

📊 FNI Methodology 📚 Knowledge Baseℹ️ Verify with original source

🛡️ Model Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

🆔 Identity & Source

id: hf-model--puxai--pii-token-filter-hard-gretel
slug: puxai--pii-token-filter-hard-gretel
source: huggingface
author: PuxAI
license: MIT
tags: transformers, safetensors, deberta-v2, token-classification, generated_from_trainer, base_model:microsoft/deberta-v3-small, base_model:finetune:microsoft/deberta-v3-small, license:mit, endpoints_compatible, region:us

⚙️ Technical Specs

architecture: DebertaV2ForTokenClassification
params billions: 0.14
context length: 512
pipeline tag: token-classification
vram gb: 1.4
vram is estimated: true
vram formula: VRAM ≈ (params * 0.75) + 0.8GB (KV) + 0.5GB (OS)

📊 Engagement & Metrics

downloads: 31
stars: 0
forks: 0

Data indexed from public sources. Updated daily.