Instructions to use xsa-dev/fingpt-compliance-agents with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xsa-dev/fingpt-compliance-agents with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B-Instruct")
model = PeftModel.from_pretrained(base_model, "xsa-dev/fingpt-compliance-agents")

Transformers

How to use xsa-dev/fingpt-compliance-agents with Transformers:

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

pipe = pipeline("text-generation", model="xsa-dev/fingpt-compliance-agents")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("xsa-dev/fingpt-compliance-agents", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xsa-dev/fingpt-compliance-agents with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xsa-dev/fingpt-compliance-agents"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xsa-dev/fingpt-compliance-agents",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/xsa-dev/fingpt-compliance-agents

SGLang

How to use xsa-dev/fingpt-compliance-agents 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 "xsa-dev/fingpt-compliance-agents" \
    --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": "xsa-dev/fingpt-compliance-agents",
		"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 "xsa-dev/fingpt-compliance-agents" \
        --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": "xsa-dev/fingpt-compliance-agents",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use xsa-dev/fingpt-compliance-agents with Docker Model Runner:
```
docker model run hf.co/xsa-dev/fingpt-compliance-agents
```

xsa-dev commited on Oct 20, 2025

Commit

cd3e6c8

verified ·

1 Parent(s): 565df3c

Upload inference_example.py with huggingface_hub

Browse files

Files changed (1) hide show

inference_example.py +24 -0

inference_example.py ADDED Viewed

	@@ -0,0 +1,24 @@

+# FinGPT Compliance Agents - Inference Example
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+import torch
+# Load the model
+base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B-Instruct")
+model = PeftModel.from_pretrained(base_model, "your-username/fingpt-compliance-agents")
+tokenizer = AutoTokenizer.from_pretrained("your-username/fingpt-compliance-agents")
+# Example usage
+def analyze_financial_text(text):
+    prompt = f"Analyze this financial text: {text}"
+    inputs = tokenizer(prompt, return_tensors="pt")
+    with torch.no_grad():
+        outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+# Test the model
+result = analyze_financial_text("Company X reported strong quarterly earnings with 15% revenue growth.")
+print(result)