---
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen3-32B
tags:
- axolotl
- base_model:adapter:Qwen/Qwen3-32B
- lora
- transformers
pipeline_tag: text-generation
model-index:
- name: outputs/qwen32b-thai
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.13.0.dev0`
```yaml
adapter: lora
base_model: Qwen/Qwen3-32B
bf16: true
flash_attention: true
gradient_checkpointing: true

datasets:
- path: /workspace/data/wangchan_fixed
  type: alpaca
  split: train

val_set_size: 0
sequence_len: 2048
train_on_inputs: false

micro_batch_size: 4
gradient_accumulation_steps: 8

optimizer: adamw_torch
learning_rate: 1.0e-4
lr_scheduler: cosine
warmup_ratio: 0.03
weight_decay: 0.01
max_grad_norm: 1.0
num_epochs: 2

lora_r: 32
lora_alpha: 64
lora_dropout: 0.05
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- down_proj
- up_proj

output_dir: ./outputs/qwen32b-thai
logging_steps: 10
save_steps: 300

```

</details><br>

# Qwen3-32B Thai LoRA

This model is a fine-tuned version of [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) on the [WangchanThaiInstruct](https://huggingface.co/datasets/airesearch/WangchanThaiInstruct) dataset for improved Thai language instruction-following capabilities.

## Model Description

This LoRA adapter enhances Qwen3-32B's ability to understand and respond to Thai language instructions across various domains including finance, general knowledge, creative writing, and classification tasks.

- **Base Model:** Qwen/Qwen3-32B
- **Fine-tuning Method:** LoRA (Low-Rank Adaptation)
- **Language:** Thai (th)
- **Training Loss:** 0.85 → 0.55

## Intended Uses & Limitations

### Intended Uses
- Thai language question answering
- Thai instruction following
- Thai content generation
- Financial domain queries in Thai

### Limitations
- Performance may vary on domains not covered in the training data
- Inherits limitations of the base Qwen3-32B model
- Primarily optimized for Thai; multilingual performance may differ from base model

## Training and Evaluation Data

### Dataset
- **Name:** [WangchanThaiInstruct](https://huggingface.co/datasets/airesearch/WangchanThaiInstruct)
- **Training Samples:** ~29,000 (after filtering sequences > 2048 tokens)
- **Format:** Alpaca-style (instruction, input, output)
- **Domains:** Finance, General Knowledge, Creative Writing, Classification, Open QA, Closed QA

## Training Procedure

### Hardware
- **GPU:** 1x NVIDIA H200 SXM (141GB VRAM)
- **Training Time:** ~10 hours

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 43
- training_steps: 1444

### Training Results

| Step | Loss |
|------|------|
| 10 | 0.85 |
| 20 | 0.78 |
| 1068 | 0.55 |
| 1444 (final) | ~0.50 |

### Framework versions

- PEFT 0.17.1
- Transformers 4.57.3
- Pytorch 2.7.1+cu126
- Datasets 4.3.0
- Tokenizers 0.22.1

## Citation

If you use this model, please cite the original dataset and base model:
```bibtex
@misc{wangchanthaiinstruct,
  title={WangchanThaiInstruct},
  author={AIResearch.in.th},
  year={2024},
  publisher={Hugging Face},
  url={https://huggingface.co/datasets/airesearch/WangchanThaiInstruct}
}

@misc{qwen3,
  title={Qwen3 Technical Report},
  author={Qwen Team},
  year={2025},
  eprint={2505.09388},
  archivePrefix={arXiv}
}