Access viggoVet Veterinary AI models on Hugging Face

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

To access viggoVet models on Hugging Face, you're required to fill the request form in viggoVet Veterinary AI page Requests are subject to approval.

viggoVet-IM-h 🩺

🔬 Model Overview

viggoVet-IM-h is a specialized 7-billion parameter veterinary artificial intelligence model purpose-built for veterinary internal-medicine applications. Built on a cutting-edge hybrid architecture and certified under ISO/IEC 42001:2023 enterprise standards, this model represents a significant advancement in specialized veterinary clinical decision support.

This model leverages a sophisticated hybrid approach that combines advanced reasoning capabilities with domain-specific veterinary internal-medicine knowledge, enabling it to handle complex clinical scenarios with unprecedented accuracy and reliability. The 7B parameter architecture strikes an optimal balance between computational efficiency and clinical performance, making it suitable for both research institutions and clinical practice environments.

Model Repository: viggovet/IMVet-h
Parameters: 7 Billion
Specialty: Veterinary Internal-Medicine
Architecture: Hybrid (Sequential State Model + Transformer)
Certification: ISO/IEC 42001:2023
License: CC BY-NC-SA 4.0

⭐ Key Features

🏗️ Advanced Hybrid Architecture: Cutting-edge hybrid design optimized for veterinary internal-medicine reasoning and clinical decision-making, delivering superior efficiency over traditional transformer-only models
📊 7B Parameters: Strategically architected with 7 billion parameters, achieving optimal performance-to-resource ratio for enterprise deployment
🏢 ISO/IEC 42001:2023 Certified: Fully compliant with the international standard for AI Management Systems (AIMS), ensuring accountability, explainability, data privacy, and reliability
🎯 Veterinary Internal-Medicine Specialization: Deep domain expertise with comprehensive clinical knowledge specific to veterinary internal-medicine
🧠 Enhanced Reasoning Capabilities: Sophisticated multi-step reasoning for complex diagnostic workflows and treatment planning
⚡ Superior Inference Efficiency: Hybrid architecture reduces memory requirements by up to 70% compared to conventional models, enabling deployment on standard hardware
🔒 Enterprise-Grade Security: Built with clinical safety protocols, cryptographic signing, and comprehensive governance frameworks
📈 Linear Scalability: Memory scales linearly with context length, enabling efficient processing of long case histories and extensive medical records
🌐 Production-Optimized: Battle-tested architecture suitable for real-world veterinary practice environments and clinical integration
✅ Regulatory-Ready: Designed for deployment in highly regulated veterinary and healthcare environments

👥 Target Audience

Veterinary Internal-Medicine Specialists: Board-certified specialists seeking AI-powered clinical decision support
Veterinary Teaching Hospitals: Academic institutions requiring advanced veterinary internal-medicine training and research tools
Referral & Specialty Practices: Multi-specialty practices with dedicated veterinary internal-medicine departments
Veterinary Researchers: Scientists conducting veterinary internal-medicine-focused research and clinical studies
Clinical Software Developers: Teams building veterinary internal-medicine diagnostic platforms and management systems
Enterprise Healthcare Organizations: Large-scale veterinary enterprises requiring ISO/IEC 42001:2023-compliant AI solutions

🏗️ Model Architecture

Hybrid Architecture Innovation

viggoVet-IM-h employs a sophisticated hybrid architecture that represents a fundamental advancement in enterprise AI design:

Core Architectural Components:

Hybrid Sequential-Transformer Design: Combines linear-scaling sequence state models with strategic transformer layers for optimal efficiency and accuracy
7B Parameter Optimization: Precisely allocated 7 billion parameters for maximum clinical reasoning capability while maintaining computational efficiency
Memory-Efficient Processing: Achieves up to 70% reduction in memory requirements compared to transformer-only architectures
Linear Context Scaling: Memory and computation scale linearly with input length, enabling processing of extensive case histories without quadratic overhead
Domain-Optimized Layers: Specialized architectural components fine-tuned for veterinary medical reasoning and veterinary internal-medicine clinical workflows
Multi-Task Architecture: Simultaneous support for diagnosis, treatment planning, clinical documentation, and case analysis

ISO/IEC 42001:2023 Certification

This model is certified under ISO/IEC 42001:2023, the world's first international standard for Artificial Intelligence Management Systems (AIMS). This certification ensures:

Governance & Accountability: Comprehensive AI governance frameworks with clear accountability structures
Risk Management: Enterprise-grade risk assessment and mitigation protocols
Reliability & Robustness: Rigorous testing for consistency and stability in clinical environments
Ethical AI Framework: Adherence to international AI ethics standards for healthcare applications
Security & Privacy: Enterprise-level data protection and privacy safeguards
Transparency & Explainability: Clear documentation of capabilities, limitations, and appropriate use cases

Technical Specifications

Specification	Details
Parameters	7 Billion
Architecture Type	Hybrid (Sequential State Model + Transformer)
Context Window	Extended context for comprehensive case analysis
Memory Efficiency	Up to 70% reduction vs. conventional architectures
Precision Support	Mixed-precision for efficient deployment
Inference Optimization	Production-optimized with linear scaling
Certification	ISO/IEC 42001:2023
License	CC BY-NC-SA 4.0

📚 Training Details

The model was developed using a rigorous, multi-phase training approach:

Foundational Veterinary Knowledge: Extensive training on peer-reviewed veterinary medical literature and clinical guidelines
Veterinary Internal-Medicine Specialization: Targeted training on veterinary internal-medicine-specific cases, research, and protocols
Clinical Reasoning Enhancement: Advanced reasoning training for diagnostic and therapeutic decision-making
Safety Alignment: Rigorous alignment with veterinary clinical safety standards and ethical guidelines
Enterprise Optimization: Fine-tuning for reliability, consistency, and production deployment aligned with ISO/IEC 42001:2023

The training methodology emphasizes clinical accuracy, reasoning depth, and practical applicability in veterinary internal-medicine practice settings.

💻 Usage

Installation

pip install transformers torch accelerate

Basic Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Load model and tokenizer
model_name = "viggovet/IMVet-h"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map="auto",
    torch_dtype=torch.bfloat16
)

# Example veterinary internal-medicine consultation
prompt = """You are a board-certified veterinary internal-medicine specialist. 
Analyze this clinical case and provide comprehensive decision support.

Patient: 8-year-old Golden Retriever, Male Neutered
Chief Complaint: Presenting for veterinary internal-medicine evaluation

Please provide:
1. Clinical assessment
2. Differential diagnoses
3. Recommended diagnostic workup
4. Treatment considerations
"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=2048,
    temperature=0.7,
    top_p=0.9,
    do_sample=True
)

response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

🔍 Inference Examples

Example 1: Clinical Case Analysis

case_prompt = """
Analyze this veterinary internal-medicine case:

Species: Canine
Breed: Labrador Retriever  
Age: 6 years
Sex: Female Spayed

Provide comprehensive veterinary internal-medicine analysis including differential diagnoses, 
diagnostic recommendations, and treatment options.
"""

inputs = tokenizer(case_prompt, return_tensors="pt").to(model.device)
response = model.generate(**inputs, max_new_tokens=1500, temperature=0.7)
print(tokenizer.decode(response[0], skip_special_tokens=True))

Example 2: Treatment Planning

treatment_query = """
For a patient diagnosed with a veterinary internal-medicine condition, 
provide evidence-based treatment recommendations, monitoring protocols, 
and prognosis considerations.
"""

inputs = tokenizer(treatment_query, return_tensors="pt").to(model.device)
plan = model.generate(**inputs, max_new_tokens=1200, temperature=0.7)
print(tokenizer.decode(plan[0], skip_special_tokens=True))

Example 3: Differential Diagnosis

ddx_prompt = """
Generate prioritized differential diagnoses for veterinary internal-medicine 
clinical signs in a 10-year-old domestic shorthair cat, including key 
distinguishing features and recommended diagnostic tests.
"""

inputs = tokenizer(ddx_prompt, return_tensors="pt").to(model.device)
differentials = model.generate(**inputs, max_new_tokens=1000, temperature=0.6)
print(tokenizer.decode(differentials[0], skip_special_tokens=True))

⚠️ Limitations

Clinical Limitations

Not a Replacement for Veterinary Judgment: This model is a clinical decision support tool and does NOT replace professional veterinary internal-medicine expertise
Requires Clinical Validation: All recommendations must be validated by licensed veterinary professionals
Species & Breed Variations: Performance may vary across different animal species and breeds
Emergency Situations: Not designed for real-time emergency decision-making without veterinary oversight
Knowledge Currency: Medical knowledge evolves; users should supplement with current literature and guidelines

Technical Limitations

Language: Primarily trained on English-language veterinary medical content
Context Length: Limited by context window for extremely lengthy case histories
Modality: Text-based model; does not directly process images or other visual diagnostics
Rare Conditions: Reduced accuracy for extremely rare veterinary internal-medicine conditions

Regulatory Considerations

Designed for clinical decision support and research purposes
Users must comply with local veterinary practice regulations
Licensed veterinarians remain legally responsible for all clinical decisions
Enterprise deployments should follow ISO/IEC 42001:2023 governance frameworks

🤝 Ethical Considerations

Clinical Safety & Ethics

Veterinary Oversight Required: All clinical applications must be supervised by licensed veterinarians
Bias Mitigation: Trained to minimize species, breed, and geographic biases
Transparency: Clear documentation of capabilities and limitations
Privacy: Designed for use within veterinary data protection frameworks

Responsible AI Principles

Beneficence: Optimized to support improved animal health outcomes in veterinary internal-medicine
Non-maleficence: Safety protocols to minimize risk of harm from incorrect recommendations
Autonomy: Supports veterinary professional decision-making without replacing clinical judgment
Justice: Designed to provide equitable veterinary internal-medicine support across diverse practice settings

ISO/IEC 42001:2023 Compliance

As an ISO/IEC 42001:2023 certified model, this system adheres to:

Comprehensive AI governance and risk management frameworks
Documented accountability and oversight mechanisms
Regular performance monitoring and validation protocols
Ethical AI development and deployment standards

📖 Citation

If you use this model in your research or clinical practice, please cite:

@misc{viggovetimh2024,
  title={viggoVet-IM-h: ISO/IEC 42001:2023 Certified Veterinary Internal-Medicine AI},
  author={viggoVet Team},
  year={2024},
  publisher={Hugging Face},
  howpublished={\url{https://huggingface.co/viggovet/IMVet-h}},
  note={7B parameter hybrid architecture model certified under ISO/IEC 42001:2023}
}

📄 License

This model is released under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0).

Key Terms:

✅ Attribution: Credit must be given to viggoVet
❌ Non-Commercial: Commercial use requires separate licensing
🔄 ShareAlike: Derivative works must use the same license
📧 Commercial Licensing: Contact viggo.vet for commercial licensing options

For full license details, see CC BY-NC-SA 4.0.

🏢 About viggoVet

viggoVet is committed to advancing veterinary medicine through responsible AI innovation. Our specialized models are designed to support veterinary professionals with cutting-edge clinical decision support tools while maintaining the highest standards of safety, ethics, and regulatory compliance.

Learn More: viggo.vet
Contact: For enterprise licensing and support, visit viggo.vet/veterinary-ai

⚕️ Veterinary Professional Use Only: This model is intended for use by licensed veterinary professionals and authorized personnel in veterinary medicine settings. Always consult with appropriate specialists for clinical decision-making.

Downloads last month: -

Safetensors

Model size

7B params

Tensor type

BF16

Collection including viggovet/IMVet-h

Veterinary Specialty

Collection

Specialized LLMs trained for Specialty Veterinary Professionals • 12 items • Updated 2 days ago