manotham/Thai-dialogue-transalate
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Apr 26, 2026License:apache-2.0Architecture:Transformer Open Weights Cold
The manotham/Thai-dialogue-transalate is a 4 billion parameter Qwen3-based instruction-tuned causal language model developed by manotham. This model is specifically fine-tuned for Thai dialogue translation, leveraging Unsloth for accelerated training. It is designed to provide efficient and accurate translation of conversational Thai language, making it suitable for applications requiring localized language processing.
Loading preview...
Overview
The manotham/Thai-dialogue-transalate is a 4 billion parameter Qwen3-based instruction-tuned model developed by manotham. It was fine-tuned from unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit using the Unsloth library, which enabled a 2x faster training process, and Huggingface's TRL library.
Key Capabilities
- Thai Dialogue Translation: Specifically optimized for translating conversational Thai language.
- Efficient Training: Benefits from Unsloth's accelerated training techniques, making it a resource-efficient model.
- Qwen3 Architecture: Built upon the Qwen3 model family, providing a robust foundation for language understanding and generation.
Good For
- Localized Applications: Ideal for developers building applications that require accurate translation of Thai dialogues.
- Resource-Constrained Environments: Its efficient training and 4B parameter size make it suitable for deployment where computational resources might be a consideration.
- Research and Development: Can serve as a base for further fine-tuning or research into Thai language processing and translation.