meetara-phi-3.5-mini-instruct-gguf

meeTARA – Phi-3.5‑3.8B‑Instruct (GGUF, Q4_K_M)

This repository contains a GGUF quantized version of microsoft/Phi-3.5-mini-instruct, prepared for use with llama.cpp and compatible runtimes, and used as the core instruct model inside the meeTARA empathetic assistant.

• Base model: microsoft/Phi-3.5-mini-instruct
• Architecture: Phi-3.5 (3.8B parameters, instruct‑tuned)
• Format: GGUF
• Quantization: Q4_K_M (good quality vs RAM / speed)
• Intended use: Standalone intelligent assistant with baked-in domain detection, emotional intelligence, and structured responses for local / offline inference.

✨ Standalone Intelligence: This GGUF model includes 20 layers of intelligence baked directly into the chat template. No backend code required - download and use with llama.cpp, Ollama, or any GGUF-compatible runtime.

---

---

Available files

More quantizations (e.g., Q5_K_M, Q8_0) can be added later to this repo as additional .gguf files.

---

Prompt format (recommended)

The model uses a Qwen‑style chat template. A simple, robust pattern is:

<|im_start|>system
You are meeTARA, an emotionally intelligent AI assistant built on top of a Phi-3.5‑3.8B‑Instruct base model. Always answer clearly, kindly, and with practical steps the user can take.
<|im_end|>
<|im_start|>user
{user_message}
<|im_end|>
<|im_start|>assistant

Example:

<|im_start|>system
You are meeTARA, an emotionally intelligent AI assistant built on top of a Phi-3.5‑3.8B‑Instruct base model. Always answer clearly, kindly, and with practical steps the user can take.
<|im_end|>
<|im_start|>user
How can I improve my sleep quality and manage stress naturally?
<|im_end|>
<|im_start|>assistant

---

Example usage (llama.cpp)

Basic interactive chat

./llama-simple-chat -m /path/to/meetara-phi-3.5-mini-instruct-gguf-Q4_K_M.gguf

With explicit system prompt

./llama-cli \
  -m /path/to/meetara-phi-3.5-mini-instruct-gguf-Q4_K_M.gguf \
  -p "<|im_start|>system You are meeTARA, an emotionally intelligent AI assistant built on top of a Phi-3.5‑3.8B‑Instruct base model. Always answer clearly, kindly, and with practical steps the user can take. <|im_end|> <|im_start|>user How can I improve my sleep quality and manage stress naturally? <|im_end|> <|im_start|>assistant"

Adjust flags like -n (max tokens), --temperature, --top_p, --top_k, etc. according to your hardware and latency/quality trade‑offs.

---

Downloading via huggingface-cli

pip install -U "huggingface_hub[cli]"

huggingface-cli download \
  meetara-phi-3.5-mini-instruct-gguf \
  --include "meetara-phi-3.5-mini-instruct-gguf-Q4_K_M.gguf" \
  --local-dir .

This will download only the Q4_K_M file into the current directory.

---

🧠 Standalone Intelligence (20-Layer Detection System)

This GGUF model includes baked-in intelligence that works without any backend code. The model automatically detects domains, emotions, intent, and context through a 20-layer detection system:

Intelligence Layers

How It Works

When a user sends a message, the chat template (baked into the GGUF) processes through these 20 layers automatically:

1. Safety Check: Refusal patterns detect harmful requests first
2. Context Analysis: Multi-word phrases, n-grams, and semantic clusters provide context
3. User Understanding: Entity patterns, intent signals, emotion blending, and persona/language detection understand the user
4. Response Adaptation: Tone, question type, and length control adapt the response style
5. Domain Selection: Weighted keyword scoring with negative keyword penalties; highest score wins
6. Output Format: Contextual structure (2–5 sections when helpful; direct answer for simple questions) with appropriate greetings/closings

Result: The model responds intelligently, empathetically, and contextually without requiring backend code.

---

Intended behavior / meeTARA flavor

Compared to the raw microsoft/Phi-3.5-mini-instruct model, this quantization includes:

• Standalone Intelligence: Works without backend - all intelligence baked into the GGUF
• 18 Domain Categories: Auto-detects healthcare, technology, business, education, and 14 more
• Emotional Intelligence: Emotion blending and persona calibration; detects worried, frustrated, urgent, etc.
• Context Awareness: Conversation memory and follow-up detection; understands multi-turn flow
• Structured Responses: Contextual structure (2–5 sections when helpful; direct answer for simple questions)
• Safety Features: Built-in refusal patterns and safety disclaimers for sensitive topics
• Warm, Supportive Tone: Responds with empathy while being precise and practical

The model is fully standalone - download and use with llama.cpp, Ollama, or any GGUF-compatible runtime. No additional backend code required.

---

📚 Usage Examples

Example 1: Healthcare Domain Detection

Input:

I've been having headaches for the past week. What could be causing this?

What Happens:

• Layer 1: Safety check passes (not harmful)
• Layer 4: Semantic cluster "pain_symptoms" detected → healthcare boost
• Layer 7: Emotion detected: "worried" (health concern)
• Layer 11: Domain detected: Healthcare (high confidence)
• Layer 14: Safety disclaimer added (healthcare topic)
• Layer 16: Contextual structure with empathetic opening (e.g. 2–5 sections when helpful)

Expected Response: Empathetic opening, clear answer and key details, practical steps, and safety disclaimer. Structure adapts to question complexity (simpler questions get a more direct answer).

---

Example 2: Technology Domain with Context Awareness

Input:

How do I fix a Python error in my code?

What Happens:

• Layer 2: Contextual pattern "python code" detected → technology domain (not snake)
• Layer 6: Intent detected: FIX → systematic troubleshooting approach
• Layer 9: Question type: troubleshooting → step-by-step format
• Layer 11: Domain detected: Technology (high confidence)
• Layer 16: Contextual structure with technical steps

Expected Response:

• Technical, step-by-step troubleshooting format
• Code examples and debugging tips
• Practical solutions prioritized

---

Example 3: Emotional Intelligence Detection

Input:

I'm so frustrated with my job search. Nothing seems to work.

What Happens:

• Layer 7: Emotion detected: frustrated → empathetic, supportive tone
• Layer 8: Tone detected: distressed → warm, encouraging response
• Layer 6: Intent detected: VENT → supportive, validating response
• Layer 11: Domain detected: Career/Professional (medium confidence)
• Layer 16: Response starts with emotional acknowledgment

Expected Response:

• Opens with empathy: "I understand how frustrating this can be..."
• Validates feelings before providing advice
• Practical, actionable steps to improve situation
• Encouraging, supportive tone throughout

---

Example 4: Multi-Domain with Priority

Input:

My friend is showing signs of depression. How can I help them?

What Happens:

• Layer 1: Safety check passes
• Layer 5: Entity pattern: third_party (helping someone else)
• Layer 7: Emotion detected: worried (concern for friend)
• Layer 11: Domain detected: Healthcare (mental health) + Psychology/Wellness
• Layer 12: Domain priority: Healthcare wins (safety-critical)
• Layer 14: Safety disclaimer added (mental health topic)
• Layer 15: Greeting acknowledges the caring nature of the question

Expected Response:

• Healthcare domain expertise applied
• Safety disclaimers about professional help
• Practical steps for supporting someone with depression
• Emphasis on professional mental health resources

---

Example 5: Follow-up Context Awareness

Conversation:

User: What are the symptoms of anxiety?
Assistant: [Provides structured response about anxiety symptoms]
User: What about panic attacks?

What Happens:

• Layer 13: Context awareness detects follow-up question
• Previous domain (Healthcare) is considered
• "panic attacks" → healthcare domain confirmed
• Response builds on previous conversation context
• No need to repeat general information

Expected Response:

• References previous conversation about anxiety
• Explains relationship between anxiety and panic attacks
• Builds on context naturally

---

Example 6: Simple vs Complex Question Adaptation

Simple Question:

What is photosynthesis?

What Happens:

• Layer 10: Response length: concise (factual question)
• Layer 9: Question type: what-is → definition format
• Layer 11: Domain: Education/Science
• Layer 16: Simplified structure (less detail needed)

Complex Question:

How does quantum computing work and what are its practical applications?

What Happens:

• Layer 10: Response length: detailed (complex topic)
• Layer 9: Question type: how-to + what-is → comprehensive format
• Layer 11: Domain: Technology + Science
• Layer 16: Full structured response with deep analysis

---

💡 Tips for Best Results

1. Be Specific: More context helps the model detect the right domain

   • ✅ "I'm worried about my chest pain" → Healthcare + Emotion detected
   • ❌ "Tell me about pain" → Less specific, lower confidence

2. Natural Language: The model understands conversational language

   • ✅ "How do I fix this bug in my Python code?"
   • ✅ "I'm frustrated with this error"

3. Follow-ups Work: The model remembers context within a conversation

   • Ask follow-up questions naturally - the model will understand

4. Emotional Cues: Expressing emotions helps the model respond empathetically

   • "I'm worried about..." → Empathetic response
   • "I'm excited to learn..." → Encouraging response

---

Credits

• Base model and original training: microsoft/Phi-3.5-mini-instruct by Microsoft.
• Quantization and meeTARA integration: meetara‑lab.

If you use this GGUF in your work, please also cite the original Phi-3.5 paper/model in addition to this repository.