LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Pii Redaction V0.3 by mattlanham

 »  All LLMs  »  mattlanham  »  Pii Redaction V0.3   URL Share it on

  4460   
  4bit   Autotrain compatible   Conversational   En   Endpoints compatible   Instruct   Mistral   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/mattlanham/pii-redaction-v0.3 

Pii Redaction V0.3 Benchmarks

LLME Score: 0.25281
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Pii Redaction V0.3 (mattlanham/pii-redaction-v0.3)

Pii Redaction V0.3 Parameters and Internals

Model Type 
text-generation-inference, transformers
Use Cases 
Areas:
data extraction, pii redaction
Primary Use Cases:
redacting personal identifiers in customer communications
Additional Notes 
Model provides structured JSON output for PII redaction and data extraction
Supported Languages 
en (fluent)
Training Details 
Data Sources:
synthetic data
Methodology:
Trained using synthetic data and Huggingface's TRL library
Training Time:
2x faster training using Unsloth
Input Output 
Input Format:
Text with potential PII
Accepted Modalities:
text
Output Format:
JSON format with redacted text and extracted data
LLM NamePii Redaction V0.3
Repository 🤗https://huggingface.co/mattlanham/pii-redaction-v0.3 
Base Model(s)  unsloth/phi-3-mini-4k-instruct-bnb-4bit   unsloth/phi-3-mini-4k-instruct-bnb-4bit
Model Size3.8b
Required VRAM7.6 GB
Updated2024-12-22
Maintainermattlanham
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.6 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Padding Token<|placeholder6|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Pii Redaction V0.3

Best Alternatives
Context / RAM
Downloads
Likes
... Instruct Unsloth Merged 16bit4K / 7.6 GB781
...Word Problems 200K Model 16bit4K / 7.6 GB38790
Porpoise14K / 7.6 GB3530
... 4K Instruct Matter 0.1 Slim A4K / 7.6 GB162
...Word Problems 200K Model 16bit4K / 7.6 GB4260
...rser User V9b Epoch 7 Lr 0.0024K / 7.6 GB180
...100 Percent Low Med Perplexity4K / 7.6 GB180
...22 Epoch7 0.002 Nosystemprompt4K / 7.6 GB190
...Af 50 Percent Low Med Nv Embed4K / 7.6 GB210
...20 Epoch7 0.002 Nosystemprompt4K / 7.6 GB190
Note: green Score (e.g. "73.2") means that the model is better than mattlanham/pii-redaction-v0.3.

Rank the Pii Redaction V0.3 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 40123 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217
  Support LLM Explorer