dearxoasis/thaidoc-finetune

TEXT GENERATIONPricing:Input $0.468 / Output $1.82Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 16, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The dearxoasis/thaidoc-finetune is an 8 billion parameter Qwen3-based language model developed by dearxoasis, fine-tuned from typhoon-ai/typhoon-s-thaillm-8b-instruct-research-preview. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed for specific applications, likely related to Thai language document processing, given its base model and fine-tuning origin.

Loading preview...

Model Overview

The dearxoasis/thaidoc-finetune is an 8 billion parameter language model, developed by dearxoasis. It is based on the Qwen3 architecture and was fine-tuned from the typhoon-ai/typhoon-s-thaillm-8b-instruct-research-preview model, indicating a specialization towards Thai language understanding and generation, particularly for document-related tasks.

Key Characteristics

  • Base Architecture: Qwen3 model family.
  • Parameter Count: 8 billion parameters, offering a balance between performance and computational efficiency.
  • Training Efficiency: The model was fine-tuned with Unsloth and Huggingface's TRL library, resulting in a 2x faster training process compared to standard methods.
  • Context Length: Supports a context length of 32768 tokens.

Potential Use Cases

Given its fine-tuning origin from a Thai LLM and the 'thaidoc' in its name, this model is likely optimized for:

  • Processing and understanding Thai language documents.
  • Instruction-following tasks in Thai.
  • Applications requiring efficient inference for Thai text.

Finetunes
2 models