---
title: QAZTECH-AZ104-Tutor-8B
canonical_url: "https://www.modelscope.ai/models/qaztechplatform/QAZTECH-AZ104-Tutor-8B"
md_url: "https://www.modelscope.ai/models/qaztechplatform/QAZTECH-AZ104-Tutor-8B.md"
repository: qaztechplatform/QAZTECH-AZ104-Tutor-8B
last_updated: 2026-10-11
license: "Apache License 2.0"
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3
architectures:
  - Qwen3ForCausalLM
base_model:
  - Qwen/Qwen3-8B
base_model_relation: finetune
parameters: 8.2B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - PyTorch
language:
  - en
  - ru
  - kk
  - ar
  - es
downloads: 4
stars: 0
---

# QAZTECH-AZ104-Tutor-8B

> QAZTECH-AZ104-Tutor-8B - An open-source model by qaztechplatform on ModelScope. QAZTECH® AZ-104 Tutor 8B (v0.2 preview)

qaztechplatform/QAZTECH-AZ104-Tutor-8B is a 8.2B-parameter text-generation model on ModelScope. licensed under Apache License 2.0. derived from Qwen/Qwen3-8B.

- **Repository**: qaztechplatform/QAZTECH-AZ104-Tutor-8B
- **License**: Apache License 2.0
- **Tasks**: text-generation
- **Parameters**: 8.2B
- **Base model**: Qwen/Qwen3-8B
- **Downloads**: 4
- **Stars**: 0
- **Last updated**: 2026-10-11

Source: https://www.modelscope.ai/models/qaztechplatform/QAZTECH-AZ104-Tutor-8B

---

# QAZTECH® AZ-104 Tutor 8B (v0.2 preview)

Multilingual engineering tutor for Microsoft Azure topics. It explains concepts, corrects misconceptions and writes certification-style practice questions with explanations, in English, Russian, Kazakh, Arabic and Spanish.

## Quick start
Ollama: `ollama run qaztech-platform/az104-tutor`

ModelScope (Transformers API):
```python
from modelscope import AutoModelForCausalLM, AutoTokenizer
m = "qaztechplatform/QAZTECH-AZ104-Tutor-8B"
tok = AutoTokenizer.from_pretrained(m)
model = AutoModelForCausalLM.from_pretrained(m, torch_dtype="auto", device_map="auto")
msgs = [{"role": "system", "content": "You are an expert engineering tutor. Reply in the student's language."},
        {"role": "user", "content": "Give me a practice question on Azure RBAC"}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, enable_thinking=False, return_tensors="pt").to(model.device)
print(tok.decode(model.generate(ids, max_new_tokens=400)[0][ids.shape[1]:], skip_special_tokens=True))
```
Use `enable_thinking=False`: the model was trained without reasoning traces.

## Training
- Base: Qwen/Qwen3-8B (Apache-2.0). LoRA (r=16, alpha=32, all linear layers), 3 epochs, lr 1e-4, bf16, merged into the base weights.
- Data: 5,107 synthetic tutoring dialogues (4,907 train / 200 held out), generated by Qwen3-30B-A3B-Instruct-2507 from Microsoft Azure documentation on role-based access control, virtual networks, Azure Resource Manager and App Service.
- Modes: explanation 1,804; misconception correction 1,613; certification-style practice questions 1,690.
- Languages: ru 1,149; kk 1,023; es 1,011; en 980; ar 944.
- Filters: question and answer in the same language, no references to unseen source text, no mixed scripts, deduplication.
- Held-out eval loss 0.795, token accuracy 0.773.

## Limitations
- Facts can be wrong: incorrect permission names and behaviours were observed in testing. Use with retrieval over official documentation (RAG) and verify against Microsoft Learn.
- Kazakh and Arabic output has not yet been reviewed by native speakers; Kazakh phrasing can be awkward.
- Coverage is limited to the four Azure documentation areas above.
- Contains no real Microsoft exam questions. Not affiliated with or endorsed by Microsoft.

## Licence and attribution
Weights: Apache-2.0. Base model: Qwen3-8B by Alibaba Cloud (Apache-2.0). Training data was derived from Microsoft Azure documentation (github.com/MicrosoftDocs/azure-docs), licensed under CC BY 4.0. Microsoft and Azure are trademarks of the Microsoft group of companies.

## Trademark
QAZTECH is a registered trade mark of AISC Technologies LTD in the United Kingdom (UK IPO nos. UK00004263700, UK00004317681, UK00004373195). The Apache-2.0 licence does not grant rights to use the QAZTECH name or logo (section 6). Derivative models must not use "QAZTECH" in their name; describe them as "based on QAZTECH Tutor".


Also on Hugging Face: https://huggingface.co/qaztech-platform/QAZTECH-AZ104-Tutor-8B