abirmed_mental_slm — Psychiatry and Mental Health Specialist Transformer

Part of the A.B.I.R Ecosystem

abirmed_mental_slm is a specialized psychiatric and mental health language model developed as part of the A.B.I.R Ecosystem and the ABIRMED Modular Medical Specialist Transformer System, a distributed artificial intelligence architecture designed to replicate real-world medical specialization using modular transformer models.

This model functions as the Psychiatry and Mental Health Specialist, designed to understand psychological symptoms, mental health disorders, behavioral conditions, and psychiatric reasoning patterns.

This is Version 1.0, with future versions planned for expanded psychiatric datasets, improved mental health reasoning accuracy, and enhanced psychological intelligence capabilities.

---

ABIRMED — Modular Medical Specialist Transformer System

ABIRMED is a modular medical AI ecosystem consisting of multiple specialist Small Language Models (SLMs), each trained for a specific medical domain. Instead of using a single large monolithic model, ABIRMED uses a distributed specialist architecture inspired by real-world clinical specialization.

Each model acts as an independent medical specialist while collectively forming a unified medical reasoning system.

This modular approach provides:

• Higher accuracy within specialized domains
• Lower computational requirements
• CPU-efficient inference capability
• Scalable and extensible medical intelligence architecture

Developed by: Abir Maheshwari
Architecture: Modular Decoder-only Transformer System
Framework: PyTorch + HuggingFace Transformers
Training Platform: Google Colab T4 GPU
License: MIT

---

Role of abirmed_mental_slm in the ABIRMED System

abirmed_mental_slm functions as the Psychiatry Specialist, equivalent to a clinical psychiatrist or mental health professional in real-world healthcare systems.

Its primary role is to provide mental health reasoning capabilities including:

• Mental health symptom interpretation
• Psychological condition understanding
• Psychiatric disorder reasoning
• Behavioral condition explanation
• Mental health education support

This model complements other ABIRMED specialist models such as diagnosis, pharmacology, pathology, emergency, cardiology, dermatology, pediatrics, and veterinary models.

---

Model Details

Model Name: abirmed_mental_slm
Version: 1.0
Developer: Abir Maheshwari
Organization: A.B.I.R Ecosystem
Model Type: Causal Language Model (Decoder-only Transformer)
Base Model: None (trained from scratch)
License: MIT

---

Technical Specifications

Architecture: Decoder-only Transformer

Parameters: ~38 Million

Transformer Layers: 8

Attention Heads: 8

Hidden Size: 512

Intermediate Size: 2048

Context Length: 256 tokens

Tokenizer: GPT-2 tokenizer with custom PAD token

Weight Sharing: Embedding and LM Head tied

Training Objective: Causal Language Modeling

Precision: FP16 mixed precision

Framework: PyTorch

Export Formats:

• safetensors
• PyTorch (.pt)

Checkpoint Support:

• Full training state resume capability

---

Training Details

Training Dataset

Primary datasets include curated psychiatric and mental health educational datasets containing:

• Mental health disorder descriptions
• Psychological symptom explanations
• Psychiatric condition narratives
• Behavioral health information

These datasets enable the model to learn relationships between psychological symptoms and mental health conditions.

---

Training Procedure

Optimizer: AdamW

Learning Rate: 5e-4

Batch Size: 8

Gradient Accumulation Steps: 2

Training Platform:

• Google Colab
• NVIDIA T4 GPU

Training Objective:

• Predict next token in psychiatric reasoning sequences

Training Format:

Instruction → Output

Converted to:

Question → Answer format

Identity training lines were included to ensure ecosystem integration.

---

Capabilities

abirmed_mental_slm is capable of:

• Understanding mental health symptoms
• Explaining psychiatric conditions
• Supporting mental health education
• Providing psychological reasoning explanations
• Supporting psychiatric research

Example:

Input: "Persistent sadness and loss of interest"

Output: "These symptoms may indicate depression, a common mental health condition affecting mood and behavior."

---

Intended Use

This model is intended for:

• Mental health education
• Medical AI research
• Psychiatric education tools
• Healthcare chatbot development
• Psychological research support

---

Out-of-Scope Use

This model is not intended for:

• Mental health diagnosis
• Clinical psychiatric treatment decisions
• Psychological treatment recommendations
• Replacement of licensed mental health professionals

This is a research model only.

---

Limitations

abirmed_mental_slm:

• Is not a licensed psychiatric system
• May produce incomplete psychological assessments
• Should not replace mental health professionals
• May lack full psychiatric accuracy

---

Design Philosophy

The ABIRMED ecosystem follows a modular specialist architecture inspired by real-world healthcare systems.

Each model specializes in a specific medical domain.

abirmed_mental_slm serves as the psychiatric intelligence specialist.

This architecture improves:

• Domain accuracy
• Reasoning reliability
• Computational efficiency
• Modular scalability

---

A.B.I.R Ecosystem Integration

abirmed_mental_slm is part of the A.B.I.R Ecosystem, which includes:

• Modular transformer intelligence systems
• Language models
• Domain-specialized AI systems
• Medical AI infrastructure

ABIRMED represents the medical intelligence division of the A.B.I.R Ecosystem.

---

Version

Version: 1.0

Future versions will include:

• Expanded psychiatric datasets
• Improved psychological reasoning accuracy
• Larger training datasets
• Enhanced mental health intelligence

---

Author

Abir Maheshwari
Independent AI Researcher
Founder, A.B.I.R Ecosystem

Hugging Face:
https://huggingface.co/abirmaheshwari

---

License

MIT License