πŸ‡ΉπŸ‡­ ByStander-7B-Thai

ByStander-7B-Thai is a specialized Thai Large Language Model (LLM) fine-tuned for Emergency Situation Guidance. It is built on top of OpenThaiGPT 1.5 (7B) and is designed to assist users during critical moments by providing life-saving instructions, identifying emergency severity, and generating scripts for communicating with emergency operators (e.g., 1669).

πŸš€ Model Highlights

  • Emergency Domain Focus: Specifically fine-tuned on Thai medical and accident emergency protocols.
  • Instructional Accuracy: Provides step-by-step guidance for CPR, choking (Heimlich Maneuver), drowning, and bleeding control.
  • Low Latency: Optimized via 4-bit quantization (GGUF) to run on consumer-grade hardware (e.g., RTX 4060).
  • Thai-Centric Intelligence: Leverages the state-of-the-art Thai reasoning capabilities of OpenThaiGPT 1.5.

πŸ›  Intended Use

  • Emergency Assistant: Providing immediate first-aid steps to bystanders.
  • Facility Finder: Identifying the type of facility (Hospital/Clinic) needed based on symptoms.
  • Emergency Scripts: Generating clear reports to tell dispatchers, ensuring accurate location and victim status delivery.

πŸ“ Prompt Format (ChatML)

This model follows the ChatML structure. Using the correct tags is essential for optimal performance.

<|im_start|>system
ΰΈ„ΰΈΈΰΈ“ΰΈ„ΰΈ·ΰΈ­ΰΈœΰΈΉΰΉ‰ΰΈŠΰΉˆΰΈ§ΰΈ’ΰΈ•ΰΈ­ΰΈšΰΈ„ΰΈ³ΰΈ–ΰΈ²ΰΈ‘ΰΈ—ΰΈ΅ΰΉˆΰΈ‰ΰΈ₯าดแΰΈ₯ΰΈ°ΰΈ‹ΰΈ·ΰΉˆΰΈ­ΰΈͺΰΈ±ΰΈ•ΰΈ’ΰΉŒ<|im_end|>
<|im_start|>user
ΰΉΰΈˆΰΉ‰ΰΈ‡ΰΉ€ΰΈ«ΰΈ•ΰΈΈ: ΰΈ‘ΰΈ΅ΰΈ„ΰΈ™ΰΈͺΰΈ³ΰΈ₯ักอาหาร ΰΈ«ΰΈ™ΰΉ‰ΰΈ²ΰΉ€ΰΈ‚ΰΈ΅ΰΈ’ΰΈ§ ΰΈ«ΰΈ²ΰΈ’ΰΉƒΰΈˆΰΉ„ΰΈ‘ΰΉˆΰΈ­ΰΈ­ΰΈ ΰΈ•ΰΉ‰ΰΈ­ΰΈ‡ΰΈ—ΰΈ³ΰΈ’ΰΈ±ΰΈ‡ΰΉ„ΰΈ‡?<|im_end|>
<|im_start|>assistant
[ΰΈ‚ΰΈ±ΰΉ‰ΰΈ™ΰΈ•ΰΈ­ΰΈ™ΰΈΰΈ²ΰΈ£ΰΈ›ΰΈΰΈ‘ΰΈžΰΈ’ΰΈ²ΰΈšΰΈ²ΰΈ₯...]
<|im_end|>
Downloads last month
253
GGUF
Model size
8B params
Architecture
qwen2
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for woraamy/ByStander-7B-Thai

Quantized
(12)
this model
Quantizations
2 models