Thait5 Instruct

🚀 ThaiT5-Instruct

ThaiT5-Instruct is a fine - tuned model based on kobkrit/thai - t5 - base. It is trained on the WangchanX Seed - Free Synthetic Instruct Thai 120k dataset, supporting multiple NLP tasks such as conversation, multiple - choice reasoning, brainstorming, question - answering, and summarization.

✨ Features

• Supports various NLP tasks including conversation, multiple - choice reasoning, brainstorming, question - answering, and summarization.
• Can be further improved with more training resources.

📦 Installation

The README does not provide installation steps, so this section is skipped.

💻 Usage Examples

Basic Usage

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("Peenipat/ThaiT5-Instruct", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("Peenipat/ThaiT5-Instruct")

input_text = "หวัดดี"

inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(input_ids=inputs["input_ids"])
output_text = tokenizer.decode(outputs[0], skip_special_tokens=True)

print(output_text)

Advanced Usage

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, pipeline

model = AutoModelForSeq2SeqLM.from_pretrained("Peenipat/ThaiT5-Instruct", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("Peenipat/ThaiT5-Instruct")

model.eval()
qa_pipeline = pipeline("text2text-generation", model=model, tokenizer=tokenizer)

def ask_question():
    context = input("Input Context: ")
    question = input("Input Question: ")
    input_text = f"Context: {context} Question: {question}"
    output = qa_pipeline(input_text,
                         max_length=60,
                         min_length=20,
                         no_repeat_ngram_size=3,
                         num_beams=5,
                         early_stopping=True)
    output_text = output[0]['generated_text']
    print("\nOutput:")
    print(output_text)

📚 Documentation

Model Description

ThaiT5-Instruct is a fine - tuned version of kobkrit/thai - t5 - base, trained on the WangchanX Seed - Free Synthetic Instruct Thai 120k dataset. This model supports various NLP tasks, including:

• Conversation
• Multiple Choice Reasoning
• Brainstorming
• Question Answering
• Summarization

The model has been trained for 13 epochs and can be further improved with more resources.

Training Details

Training Loss per Epoch:

[2.2463, 1.7010, 1.5261, 1.4626, 1.4085, 1.3844, 1.3647, 1.3442, 1.3373, 1.3182, 1.3169, 1.3016]

Validation Loss per Epoch:

[1.4781, 1.3761, 1.3131, 1.2775, 1.2549, 1.2364, 1.2226, 1.2141, 1.2043, 1.1995, 1.1954, 1.1929]

Evaluation Results

The model was evaluated using several NLP metrics, with the following results:

Limitations & Future Improvements

• The model can be further improved with additional training resources.
• Performance on complex reasoning tasks may require further fine - tuning on domain - specific datasets.
• The model does not possess general intelligence like ChatGPT, Gemini, or other advanced AI models. It excels at extracting answers from given contexts rather than generating knowledge independently.

🔧 Technical Details

The model is based on the kobkrit/thai - t5 - base architecture and is fine - tuned on the WangchanX Seed - Free Synthetic Instruct Thai 120k dataset. Training was carried out for 13 epochs with specific hyperparameters such as a batch size per device of 32, gradient accumulation steps of 2, and using the AdamW optimizer. The model's performance was evaluated using metrics like ROUGE, BLEU, and Exact Match.

📄 License

The model is released under the MIT license.

📖 Citation

If you use this model, please cite it as follows:

@misc{PeenipatThaiT5Instruct,
  title={ThaiT5-Instruct},
  author={Peenipat},
  year={2025},
  publisher={Hugging Face},
  url={https://huggingface.co/Peenipat/ThaiT5-Instruct}
}