Text Generation
Transformers
PEFT
llama
disaster-management
emergency-response
humanitarian-ai
multilingual
fine-tuned
qlora
lora
llama3
conversational
4-bit precision
bitsandbytes
Instructions to use drdeveloper88/WorldDisasterLM-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
Upload WorldDisasterLM-8B source code: FastAPI backend, training pipeline, 11-language support
495526b | import json | |
| from fastapi import APIRouter | |
| from fastapi.responses import StreamingResponse | |
| from backend.app.models.schemas import ( | |
| ChatRequest, | |
| ChatResponse, | |
| IncidentClassificationRequest, | |
| IncidentClassificationResponse, | |
| RiskAssessmentRequest, | |
| RiskAssessmentResponse, | |
| ) | |
| from backend.app.services.inference_service import classify_incident, generate_response, stream_response | |
| from backend.app.services.risk_engine import compute_risk | |
| router = APIRouter(prefix="/v1", tags=["worlddisasterlm"]) | |
| def chat(request: ChatRequest) -> ChatResponse: | |
| return generate_response(request.messages, language=request.language, region=request.region) | |
| async def chat_stream(request: ChatRequest) -> StreamingResponse: | |
| async def event_stream(): | |
| async for chunk in stream_response(request.messages, language=request.language, region=request.region): | |
| yield f"data: {json.dumps({'token': chunk})}\n\n" | |
| yield "data: [DONE]\n\n" | |
| return StreamingResponse(event_stream(), media_type="text/event-stream") | |
| def risk_score(request: RiskAssessmentRequest) -> RiskAssessmentResponse: | |
| return compute_risk( | |
| hazard_type=request.hazard_type, | |
| vulnerability_index=request.vulnerability_index, | |
| exposure_index=request.exposure_index, | |
| ) | |
| def classify(request: IncidentClassificationRequest) -> IncidentClassificationResponse: | |
| return classify_incident(request.text) | |