Instructions to use baarish/property-query-parser with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use baarish/property-query-parser with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="baarish/property-query-parser")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("baarish/property-query-parser", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use baarish/property-query-parser with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "baarish/property-query-parser" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "baarish/property-query-parser", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/baarish/property-query-parser
- SGLang
How to use baarish/property-query-parser 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 "baarish/property-query-parser" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "baarish/property-query-parser", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "baarish/property-query-parser" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "baarish/property-query-parser", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use baarish/property-query-parser with Docker Model Runner:
docker model run hf.co/baarish/property-query-parser
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,26 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: "en"
|
| 3 |
+
library_name: "transformers"
|
| 4 |
+
pipeline_tag: "text2text-generation"
|
| 5 |
+
base_model: "google/flan-t5-base"
|
| 6 |
+
license: "apache-2.0"
|
| 7 |
+
tags:
|
| 8 |
+
- text2text
|
| 9 |
+
- property
|
| 10 |
+
- query-parser
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# 🏠 Property Query Parser
|
| 14 |
+
|
| 15 |
+
This model helps extract structured information (like BHK, location, and possession date) from natural language property queries.
|
| 16 |
+
|
| 17 |
+
Example usage:
|
| 18 |
+
|
| 19 |
+
```python
|
| 20 |
+
from transformers import pipeline
|
| 21 |
+
|
| 22 |
+
pipe = pipeline("text2text-generation", model="baarish/property-query-parser")
|
| 23 |
+
|
| 24 |
+
query = "Show me 2BHK flats in Pune with possession in 2025"
|
| 25 |
+
result = pipe(query)
|
| 26 |
+
print(result[0]['generated_text'])
|