Tbata7/FortuneQwen3_4b
Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Dec 29, 2025License:otherArchitecture:Transformer0.0K Warm

FortuneQwen3_4b is a 4 billion parameter language model developed by Tbata7, based on the Qwen3 architecture. This model is specifically fine-tuned for fortune-telling and divination tasks, supporting both Chinese and English. It features a substantial 32768 token context window, making it suitable for detailed interpretive queries. The model is available in various formats including GGUF for `llama.cpp` and Ollama, and Safetensors for Transformers-based inference.

Loading preview...

FortuneQwen3_4b: Specialized for Fortune Telling

FortuneQwen3_4b is a 4 billion parameter model built upon the Qwen3 architecture, specifically fine-tuned by Tbata7 for fortune-telling and divination tasks, including I Ching interpretation. It supports both Chinese and English languages and boasts a significant 32768 token context window, allowing for comprehensive analysis of user queries.

Key Capabilities & Features

  • Specialized Task: Dedicated to generating responses for fortune-telling and divination.
  • Base Architecture: Utilizes the robust Qwen3 framework.
  • Multilingual Support: Processes queries in both Chinese (zh) and English (en).
  • Flexible Deployment: Provided in multiple formats for ease of use:
    • GGUF Quantized Models: Optimized for llama.cpp and Ollama (e.g., FortuneQwen3_4b_q8_0.gguf).
    • Modelfile: Pre-configured for direct import into Ollama, including system prompts.
    • Hugging Face Safetensors: Full model parameters with merged LoRA weights, suitable for Transformers-based inference or further fine-tuning.
  • Advanced Customization: Users can export custom GGUF files with different quantization precisions (e.g., FP16, Int8, q4_k_m) using llama.cpp tools.

Good For

  • Entertainment and Research: Primarily intended for recreational and academic exploration of AI in divination.
  • Ollama Users: Quick setup and deployment using provided Modelfile and GGUF.
  • llama.cpp Enthusiasts: Direct use of GGUF files for local inference.
  • Developers: Access to Safetensors for custom quantization or further fine-tuning within the Transformers ecosystem.