Instructions to use propertypilot/property-pilot-generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use propertypilot/property-pilot-generator with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "propertypilot/property-pilot-generator")

Transformers

How to use propertypilot/property-pilot-generator with Transformers:

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

pipe = pipeline("text-generation", model="propertypilot/property-pilot-generator")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("propertypilot/property-pilot-generator", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use propertypilot/property-pilot-generator with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/propertypilot/property-pilot-generator

SGLang

How to use propertypilot/property-pilot-generator 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 "propertypilot/property-pilot-generator" \
    --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": "propertypilot/property-pilot-generator",
		"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 "propertypilot/property-pilot-generator" \
        --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": "propertypilot/property-pilot-generator",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use propertypilot/property-pilot-generator with Docker Model Runner:
```
docker model run hf.co/propertypilot/property-pilot-generator
```

0tizm0 commited on 24 days ago

Commit

c569c61

verified ·

1 Parent(s): 80005ba

Add training_args.bin

Browse files

Files changed (1) hide show

training_args.bin +3 -0

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a09bd78669c001974beb2d4abc194ed91cc0ac96c99eefa0ce9ee913f2a19a00
+size 5368