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

Llama Guard Quant by tybrs

 »  All LLMs  »  tybrs  »  Llama Guard Quant   URL Share it on

  429   
  Arxiv:2312.06674   Arxiv:2403.13031   Autotrain compatible Base model:meta-llama/meta-lla... Base model:quantized:meta-llam...   Conversational   En   Endpoints compatible   Facebook   Gguf   Llama   Llama-3   Meta   Pytorch   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/tybrs/llama-guard-quant 

Llama Guard Quant Benchmarks

LLME Score: 0.2146
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama Guard Quant (tybrs/llama-guard-quant)

Llama Guard Quant Parameters and Internals

Model Type 
text generation, content moderation, response classification
Use Cases 
Areas:
content moderation, safer AI interactions
Applications:
LLM-based applications requiring safety evaluations
Primary Use Cases:
classifying content for safety in both prompts and responses
Limitations:
may be susceptible to adversarial attacks, needs additional components for complete safety coverage
Considerations:
Customization might be required for certain use cases.
Additional Notes 
Supports 11 of the 13 MLCommons AI Safety taxonomy categories.
Supported Languages 
en (fluent)
Training Details 
Methodology:
fine-tuned for safety classification
Model Architecture:
Llama 3-based LLM safeguard model
Safety Evaluation 
Methodologies:
safety labels prediction based on MLCommons taxonomy
Findings:
detects harmful content across 11 different categories
Risk Categories:
misinformation, bias, adversarial attacks
Ethical Considerations:
Focus on reducing false positive and false negative rates to avoid over- or under-moderation.
Responsible Ai Considerations 
Fairness:
The model's design aims to avoid introducing bias during moderation.
Transparency:
Describes methodology used for classification.
Accountability:
Meta and developers are accountable for deploying this model safely.
Mitigation Strategies:
Combination of ML models and external components to ensure safe use.
Input Output 
Input Format:
Text
Accepted Modalities:
text
Output Format:
Classified text indicating safety category
Performance Tips:
Implement external components for heightened safety.
LLM NameLlama Guard Quant
Repository 🤗https://huggingface.co/tybrs/llama-guard-quant 
Base Model(s)  Meta Llama Guard 2 8B   meta-llama/Meta-Llama-Guard-2-8B
Model Size8b
Required VRAM3.2 GB
Updated2024-12-22
Maintainertybrs
Model Typellama
Model Files  3.2 GB   4.3 GB   4.0 GB   3.7 GB   4.7 GB   5.1 GB   4.9 GB   4.7 GB   5.6 GB   6.1 GB   5.7 GB   5.6 GB   6.6 GB   8.5 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.40.0.dev0
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama Guard Quant

Best Alternatives
Context / RAM
Downloads
Likes
...truct Gradient 1048K IMat GGUF1024K / 2 GB2886
...B Instruct Gradient 1048K GGUF1024K / 3.2 GB1743
Unhinged Llama3 8B 524K512K / 26.5 GB250
Llama 3 8B Instruct 262K GGUF256K / 3.2 GB1682
... 8B Instruct Reasoner 1o1 V0.3128K / 16.1 GB2247
Reflection Llama 3.1 8B128K / 16.1 GB305117
Alpaca Llama3.1 8B128K / 16.1 GB60
...lama 3.1 Cantonese 8B Instruct128K / 16.1 GB6385
... Horizon AI Korean Advanced 8B128K / 16.1 GB7920
ProductLlama V2128K / 16.1 GB210
Note: green Score (e.g. "73.2") means that the model is better than tybrs/llama-guard-quant.

Rank the Llama Guard Quant 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? 40066 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