Instructions to use drdeveloper88/WorldDisasterLM-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use drdeveloper88/WorldDisasterLM-8B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="drdeveloper88/WorldDisasterLM-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("drdeveloper88/WorldDisasterLM-8B")
model = AutoModelForCausalLM.from_pretrained("drdeveloper88/WorldDisasterLM-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use drdeveloper88/WorldDisasterLM-8B with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use drdeveloper88/WorldDisasterLM-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "drdeveloper88/WorldDisasterLM-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "drdeveloper88/WorldDisasterLM-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/drdeveloper88/WorldDisasterLM-8B

SGLang

How to use drdeveloper88/WorldDisasterLM-8B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "drdeveloper88/WorldDisasterLM-8B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "drdeveloper88/WorldDisasterLM-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "drdeveloper88/WorldDisasterLM-8B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "drdeveloper88/WorldDisasterLM-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use drdeveloper88/WorldDisasterLM-8B with Docker Model Runner:
```
docker model run hf.co/drdeveloper88/WorldDisasterLM-8B
```

WorldDisasterLM-8B / hf_space /README.md

drdeveloper88

Upload WorldDisasterLM-8B source code: FastAPI backend, training pipeline, 11-language support

495526b 18 days ago

preview code

Raw

History Blame Contribute Delete

2.34 kB

metadata

title: WorldDisasterLM-8B
emoji: 🌍
colorFrom: red
colorTo: pink
sdk: gradio
app_file: app.py
pinned: true
license: other
tags:
  - disaster-management
  - emergency-response
  - humanitarian-ai
  - multilingual
  - fine-tuned
  - qlora
  - text-generation
short_description: Multilingual disaster guidance in 11 languages

🌍 WorldDisasterLM-8B

Open Foundation Model for Global Disaster Intelligence

WorldDisasterLM-8B is an instruction-tuned language model built on Meta Llama 3.1 8B Instruct, domain-adapted on global humanitarian disaster data for emergency guidance, risk assessment, and crisis intelligence — across 11 languages.

Features

🗣️ 11 Languages — English, Nepali, Spanish, French, Arabic, Hindi, Telugu, Chinese, Japanese, Korean, Portuguese
🏔️ Nepal-first — Nepali (Devanagari) with NDRRMA citations
📊 Risk Scoring — Composite disaster risk calculation (vulnerability × exposure)
⚡ Live Demo — Ask emergency questions, get actionable guidance instantly
🌐 Global Coverage — Earthquakes, floods, cyclones, wildfires, tsunamis, landslides

Training Data Sources

Source	Description
ReliefWeb	Humanitarian reports and disaster assessments
USGS	Earthquake catalog (M≥4.0, 10-year archive)
NOAA	Weather alerts and severe weather events
GDACS	Global disaster alert coordination events
OpenFEMA	US federal disaster declarations
WHO	Disease outbreak news and public health alerts

Try It

Type any disaster-related question in your language:

English: "What should I do immediately after an earthquake?"
Nepali: "भूकम्पको बेला के गर्ने?"
Spanish: "¿Qué hacer durante una inundación?"
Arabic: "ما الذي يجب فعله أثناء الإعصار؟"

Safety Notice

⚠️ This model is for informational and educational purposes only. Always follow official emergency orders from local authorities. Do not use as a sole source for life-safety decisions.

Citation

@misc{worlddisasterlm2026,
  title  = {WorldDisasterLM: Open Foundation Model for Global Disaster Management},
  year   = {2026},
  url    = {https://huggingface.co/spaces/YOUR_HF_USERNAME/WorldDisasterLM-8B}
}