---

license: apache-2.0

base_model: Qwen/Qwen3.8-27B

tags:

- meetara

- gguf

- quantized

- base

- conversational-ai

- emotional-intelligence

- structured-responses

- qwen

library_name: llama.cpp

quantized_by: meetara

---

meeTARA – Qwen3‑Unknown‑Base (GGUF, Q4_K_M)

This repository contains a GGUF quantized version of Qwen/Qwen3.8-27B, prepared for use with llama.cpp and compatible runtimes, and used as the core base model inside the meeTARA empathetic assistant.

• Base model: Qwen/Qwen3.8-27B
• Architecture: Qwen3 (Unknown parameters, base‑tuned)
• Format: GGUF
• Quantization: Q4_K_M (good quality vs RAM / speed)
• Intended use: Local GGUF packaging of the upstream model for meeTARA-compatible inference and prompting.

> ✨ 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

| Filename | Quant type | Size | Notes |

| -------- | ---------- | ---- | ----- |

| meetara-qwen3.8-qwen3.8-27b-gguf-Q4_K_M.gguf | Q4_K_M | ~15.7G | Default quant, recommended |

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 Qwen3‑Unknown‑Base 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 Qwen3‑Unknown‑Base 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-qwen3.8-qwen3.8-27b-gguf-Q4_K_M.gguf

With explicit system prompt

./llama-cli \
  -m /path/to/meetara-qwen3.8-qwen3.8-27b-gguf-Q4_K_M.gguf \
  -p "<|im_start|>system You are meeTARA, an emotionally intelligent AI assistant built on top of a Qwen3‑Unknown‑Base 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-qwen3.8-qwen3.8-27b-gguf \
  --include "meetara-qwen3.8-qwen3.8-27b-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

| Layer | Feature | Description |

|-------|---------|-------------|

| 1 | 🚨 Refusal Patterns | Safety-first harmful request detection |

| 2 | 🧩 Contextual Patterns | Multi-word phrase disambiguation (python code vs snake) |

| 3 | 📊 N-gram Patterns | Bigram/trigram detection for better context |

| 4 | 🔗 Semantic Clusters | Related keyword groups boost domain confidence |

| 5 | 👤 Entity Patterns | Personal context, time-sensitive, beginner/expert |

| 6 | 🎯 Intent Signals | What user wants: learn, fix, decide, create, validate |

| 7 | 💙 Emotion Blending | Detects co-occurring emotions, blends composite hints |

| 8 | 🎭 Tone Detection | Mirrors user style: casual, formal, technical |

| 9 | ❓ Question Type | Adapts format: yes/no, how-to, comparison |

| 10 | 📏 Response Length | Concise/standard/detailed based on signals |

| 11 | ⚖️ Weighted Domain Score | High/medium/low keyword weights + negative penalties |

| 12 | 🏆 Score-Based Selection | Highest score wins; priority only for ties |

| 13 | 🔄 Conversation Memory | Multi-turn depth tracking + domain shift awareness |

| 14 | ⚠️ Safety Disclaimers | Auto-adds warnings for healthcare, legal, crisis |

| 15 | 👋 Greeting/Closing | Natural conversation flow, domain-specific |

| 16 | 📝 Structured Responses | Contextual structure (adapt sections to question) |

| 17 | 🎓 Persona Calibration | Adapts expertise level: beginner/intermediate/expert |

| 18 | 🌐 Language Detection | Detects non-English cues, responds in user's language |

| 19 | 📊 Confidence Scoring | Multi-signal confidence (keywords + clusters + ngrams) |

| 20 | 🛡️ Negative Keywords | Penalizes false-positive cross-domain keywords |

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 upstream 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

Credits

• Base model and original training: Qwen/Qwen3.8-27B by Alibaba Cloud's Tongyi Lab.
• Quantization and meeTARA integration: meetara‑lab.

If you use this GGUF in your work, please also cite the original Qwen3 paper/model in addition to this repository.