Instructions to use woraamy/ByStander-7B-Thai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use woraamy/ByStander-7B-Thai with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="woraamy/ByStander-7B-Thai",
	filename="bystander_q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use woraamy/ByStander-7B-Thai with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf woraamy/ByStander-7B-Thai:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf woraamy/ByStander-7B-Thai:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf woraamy/ByStander-7B-Thai:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf woraamy/ByStander-7B-Thai:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf woraamy/ByStander-7B-Thai:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf woraamy/ByStander-7B-Thai:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf woraamy/ByStander-7B-Thai:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf woraamy/ByStander-7B-Thai:Q4_K_M

Use Docker

docker model run hf.co/woraamy/ByStander-7B-Thai:Q4_K_M

LM Studio
Jan

vLLM

How to use woraamy/ByStander-7B-Thai with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "woraamy/ByStander-7B-Thai"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "woraamy/ByStander-7B-Thai",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/woraamy/ByStander-7B-Thai:Q4_K_M

Ollama
How to use woraamy/ByStander-7B-Thai with Ollama:
```
ollama run hf.co/woraamy/ByStander-7B-Thai:Q4_K_M
```

Unsloth Studio new

How to use woraamy/ByStander-7B-Thai with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for woraamy/ByStander-7B-Thai to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for woraamy/ByStander-7B-Thai to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for woraamy/ByStander-7B-Thai to start chatting

Pi new

How to use woraamy/ByStander-7B-Thai with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf woraamy/ByStander-7B-Thai:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "woraamy/ByStander-7B-Thai:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use woraamy/ByStander-7B-Thai with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf woraamy/ByStander-7B-Thai:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default woraamy/ByStander-7B-Thai:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use woraamy/ByStander-7B-Thai with Docker Model Runner:
```
docker model run hf.co/woraamy/ByStander-7B-Thai:Q4_K_M
```

Lemonade

How to use woraamy/ByStander-7B-Thai with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull woraamy/ByStander-7B-Thai:Q4_K_M

Run and chat with the model

lemonade run user.ByStander-7B-Thai-Q4_K_M

List all available models

lemonade list

🇹🇭 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).

🚀 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.

🛠 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.

📝 Prompt Format (ChatML)

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

<|im_start|>system
คุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์<|im_end|>
<|im_start|>user
แจ้งเหตุ: มีคนสำลักอาหาร หน้าเขียว หายใจไม่ออก ต้องทำยังไง?<|im_end|>
<|im_start|>assistant
[ขั้นตอนการปฐมพยาบาล...]
<|im_end|>

Downloads last month: 26

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for woraamy/ByStander-7B-Thai

Base model

openthaigpt/openthaigpt1.5-7b-instruct

Quantized

(12)

this model

Quantizations

2 models