Instructions to use betterdataai/PII_DETECTION_MODEL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use betterdataai/PII_DETECTION_MODEL with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("betterdataai/PII_DETECTION_MODEL")
model = AutoModelForCausalLM.from_pretrained("betterdataai/PII_DETECTION_MODEL", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use betterdataai/PII_DETECTION_MODEL with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/betterdataai/PII_DETECTION_MODEL

SGLang

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

Docker Model Runner
How to use betterdataai/PII_DETECTION_MODEL with Docker Model Runner:
```
docker model run hf.co/betterdataai/PII_DETECTION_MODEL
```

srini98 commited on Aug 8, 2024

Commit

6aa03ed

1 Parent(s): 6800379

README

Browse files

Files changed (1) hide show

README.md +5 -9

README.md CHANGED Viewed

@@ -96,21 +96,17 @@ print(pii_classes)
 ### Testing Data, Factors & Metrics
 #### Testing Data
-1. We developed an in house testset that we evaluate the model on. The test set was manually annotated to ensure high quality of the test set.
 #### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
 ## Model Card Authors

 ### Testing Data, Factors & Metrics
 #### Testing Data
+1. We developed an in house testset that we evaluate the model on. The test set was manually annotated to ensure high quality of the test set. The test set mainly comprises of financial documents , contracts etc across all the 7 languages, covering all the classes.
 #### Metrics
+1. We used precision , recall and F1 score to evaluate the models output with the ground truth.
+We consider precision and recall to be:
+Precision: The ratio of correctly identified PII instances to the total identified instances.
+Recall: The ratio of correctly identified PII instances to the total actual instances in the dataset.
 ## Model Card Authors