Instructions to use nazifmhd/phi3-mini-compliance-extractor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nazifmhd/phi3-mini-compliance-extractor with Transformers:

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

pipe = pipeline("text-generation", model="nazifmhd/phi3-mini-compliance-extractor", trust_remote_code=True)
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("nazifmhd/phi3-mini-compliance-extractor", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nazifmhd/phi3-mini-compliance-extractor", trust_remote_code=True, 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]:]))

PEFT
How to use nazifmhd/phi3-mini-compliance-extractor with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nazifmhd/phi3-mini-compliance-extractor with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nazifmhd/phi3-mini-compliance-extractor"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nazifmhd/phi3-mini-compliance-extractor",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nazifmhd/phi3-mini-compliance-extractor

SGLang

How to use nazifmhd/phi3-mini-compliance-extractor 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 "nazifmhd/phi3-mini-compliance-extractor" \
    --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": "nazifmhd/phi3-mini-compliance-extractor",
		"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 "nazifmhd/phi3-mini-compliance-extractor" \
        --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": "nazifmhd/phi3-mini-compliance-extractor",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nazifmhd/phi3-mini-compliance-extractor with Docker Model Runner:
```
docker model run hf.co/nazifmhd/phi3-mini-compliance-extractor
```

Phi-3-mini compliance clause extractor (QLoRA, merged)

Fine-tuned from microsoft/Phi-3-mini-4k-instruct with QLoRA (4-bit NF4, r=16, alpha=32) to turn a financial contract/policy clause into JSON: {clause_type, obligation, party_responsible, trigger_condition, risk_flag}.

Training data: synthetic clauses generated by openai/gpt-oss-120b (teacher != student). Built for the CDAZZDEV Senior MLE assessment (Task 2). Not for production legal use.

epoch	train loss	val loss
0		0.4103
1	0.2877	0.1836
2	0.1787	0.1678
3	0.1455	0.1682

Use the system prompt in prompts/student_system_prompt.txt of the source repository.

Downloads last month: 399

Safetensors

Model size

4B params

Tensor type

F16

Model tree for nazifmhd/phi3-mini-compliance-extractor

Base model

microsoft/Phi-3-mini-4k-instruct

Finetuned

(1122)

this model