Add Qwen3-0.6B language model support to pythainlp.lm

[Copilot]

What does this changes

Adds support for Alibaba Cloud's Qwen3-0.6B model to the pythainlp.lm module.

What was wrong

The issue requested adding Qwen/Qwen3-0.6B to pythainlp.lm as a lightweight model option suitable for small tasks.

How this fixes it

New Qwen3 wrapper class (pythainlp/lm/qwen3.py):

• load_model(): Loads Qwen3-0.6B from HuggingFace with configurable device and dtype
• generate(): Basic text generation from prompts
• chat(): Chat-based generation with message history support
• Proper device handling using .to() method
• Graceful error handling with validation
• File uses 2026 copyright year as it's newly created in 2026

Module integration:

• Exported from pythainlp.lm with conditional import
• Falls back to helpful error when dependencies missing
• Added qwen3 optional dependency group (torch>=1.0.0, transformers>=4.22.1) in alphabetical order

Tests:

• Tests added in tests/extra/testx_lm.py for Qwen3 functionality
• Tests gracefully skip when optional dependencies are not installed

Compatibility:

• Merged dev branch to include Python 3.13 compatibility fixes
• All tests pass with the latest changes

Usage example:

from pythainlp.lm import Qwen3
import torch

# Install with: pip install pythainlp[qwen3]

model = Qwen3()
model.load_model(device="cpu", torch_dtype=torch.bfloat16)

# Basic generation
result = model.generate("สวัสดี")

# Chat format
messages = [{"role": "user", "content": "สวัสดีครับ"}]
response = model.chat(messages)

Your checklist for this pull request

• Passed code styles and structures
• Passed code linting checks and unit test

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Add Qwen/Qwen3-0.6B to pythainlp.lm</issue_title>
<issue_description>I found Qwen/Qwen3-0.6B. It is good enough for small tasks. I think we can add Qwen/Qwen3-0.6B to pythainlp.lm.

Not using

Model: https://huggingface.co/Qwen/Qwen3-0.6B

Apache license 2.0</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes Add Qwen/Qwen3-0.6B to pythainlp.lm #1112

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.

[wannaphong]

@copilot move test to tests/extra

[Copilot]

@copilot move test to tests/extra

Done. Moved Qwen3 tests to tests/extra/testx_lm.py and reverted tests/core/test_lm.py to its original state. Commit: 2018813

[bact]

@copilot There are changes in dev branch to fix the errors occured in Python 3.13. Merge the changes and run the tests again.

[Copilot]

@copilot There are changes in dev branch to fix the errors occured in Python 3.13. Merge the changes and run the tests again.

Merged dev branch with Python 3.13 fixes. All tests pass. Merge commit: 0d104dd

[sonarqubecloud]

Quality Gate passed

Issues
0 New issues
0 Accepted issues

Measures
0 Security Hotspots
0.0% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarQube Cloud

[coveralls]

coverage: 53.298% (-0.3%) from 53.624%
when pulling 0d104dd on copilot/add-qwen3-0-6b-model
into 65e6c54 on dev.