Instructions to use sriram1983007/SRA-RiskGate-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sriram1983007/SRA-RiskGate-4B with Transformers:

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

pipe = pipeline("text-generation", model="sriram1983007/SRA-RiskGate-4B")
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("sriram1983007/SRA-RiskGate-4B")
model = AutoModelForCausalLM.from_pretrained("sriram1983007/SRA-RiskGate-4B", 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 sriram1983007/SRA-RiskGate-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sriram1983007/SRA-RiskGate-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sriram1983007/SRA-RiskGate-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sriram1983007/SRA-RiskGate-4B

SGLang

How to use sriram1983007/SRA-RiskGate-4B 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 "sriram1983007/SRA-RiskGate-4B" \
    --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": "sriram1983007/SRA-RiskGate-4B",
		"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 "sriram1983007/SRA-RiskGate-4B" \
        --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": "sriram1983007/SRA-RiskGate-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sriram1983007/SRA-RiskGate-4B with Docker Model Runner:
```
docker model run hf.co/sriram1983007/SRA-RiskGate-4B
```

sriram1983007 commited on 1 day ago

Commit

5ab2b02

verified ·

1 Parent(s): 668c732

Card: badges for the Nov 2026 live runs; MCP eleven tools

Browse files

Files changed (1) hide show

README.md +7 -1

README.md CHANGED Viewed

@@ -115,6 +115,10 @@ model-index:
 [![alphaXiv](https://img.shields.io/badge/alphaXiv-Paper-b31b1b?style=for-the-badge)](https://www.alphaxiv.org/abs/2610.sra-riskgate-stablecoin-payment-safety)
 [![YouTube demo](https://img.shields.io/badge/YouTube-Base%20Sepolia%20demo-FF0000?style=for-the-badge&logo=youtube&logoColor=white)](https://www.youtube.com/watch?v=NeyFklYSfkA)
 [![YouTube demo](https://img.shields.io/badge/YouTube-Circle%20Arc%20demo-FF0000?style=for-the-badge&logo=youtube&logoColor=white)](https://www.youtube.com/watch?v=mPinl8ikUlE)
 ![Page views](https://hits.sh/huggingface.co/sriram1983007/SRA-RiskGate-4B.svg?style=for-the-badge&label=Page%20views&color=6b3fe0&labelColor=555555)
 **SRA-RiskGate-4B checks a stablecoin payment before an AI agent sends it, and answers `approve`, `hold` or `reject`** with reason codes. It is a 4B model, fine-tuned from `Qwen/Qwen3-4B-Instruct-2507`, that runs on a laptop.
@@ -175,7 +179,7 @@ If this is useful for your agent, a ❤️ like on this page helps others find i
 ## 🔌 Use It From an AI Agent (MCP)
-[`sra-riskgate-mcp`](https://pypi.org/project/sra-riskgate-mcp/) gives Claude Desktop, Cursor and other MCP clients nine tools to call **before** paying:
 | Tool | What it does | Needs |
 | --- | --- | --- |
@@ -187,6 +191,8 @@ If this is useful for your agent, a ❤️ like on this page helps others find i
 | `check_circle_wallets_request` | The same checks for a Circle Wallets API request (transfer, contract execution, signing) before it is sent to Circle; approvals, raw messages and wallet upgrades are held | Nothing |
 | `check_delegation` | An EIP-7702 authorization before signing: always held, naming the contract and whether it is valid on every chain | Nothing |
 | `check_user_operation` | An ERC-4337 UserOperation from a smart account (Coinbase Smart Wallet, Safe, Kernel, Nexus, SimpleAccount), call by call: an approval hidden in a batch is held, payments to the same payee are summed | Nothing |
 | `check_payment_with_model` | Full review by SRA-RiskGate-4B over your policy, the payment and your verification results | This model served locally (for example with Ollama) |
 ```json

 [![alphaXiv](https://img.shields.io/badge/alphaXiv-Paper-b31b1b?style=for-the-badge)](https://www.alphaxiv.org/abs/2610.sra-riskgate-stablecoin-payment-safety)
 [![YouTube demo](https://img.shields.io/badge/YouTube-Base%20Sepolia%20demo-FF0000?style=for-the-badge&logo=youtube&logoColor=white)](https://www.youtube.com/watch?v=NeyFklYSfkA)
 [![YouTube demo](https://img.shields.io/badge/YouTube-Circle%20Arc%20demo-FF0000?style=for-the-badge&logo=youtube&logoColor=white)](https://www.youtube.com/watch?v=mPinl8ikUlE)
+[![Verified on chain](https://img.shields.io/badge/Verified%20on%20chain-Base%20Sepolia-0052FF?style=for-the-badge&logo=coinbase&logoColor=white)](https://sepolia.basescan.org/tx/0xf12e9084becefd94fa6e26e54761fbfc8f3c04215d7fc724d0fca6077ba084fc)
+[![Independently re-checked](https://img.shields.io/badge/Re--checked%20by-Flow%20Executor-2EA44F?style=for-the-badge)](https://flow-kg4x.vercel.app/row)
+[![Circle Gateway](https://img.shields.io/badge/Circle%20Gateway-settled%20on%20Arc%20testnet-3D5AFE?style=for-the-badge)](https://gist.github.com/sriram1983007-dev/8cd44e78adec20a0157368ec38c2fb42)
+[![Grok agent test](https://img.shields.io/badge/Grok%20agent%20test-APPROVE%20%C2%B7%20HOLD%20%C2%B7%20REJECT-111111?style=for-the-badge&logo=x&logoColor=white)](https://gist.github.com/sriram1983007-dev/1555e11a57682496f710a8224415c9e2)
 ![Page views](https://hits.sh/huggingface.co/sriram1983007/SRA-RiskGate-4B.svg?style=for-the-badge&label=Page%20views&color=6b3fe0&labelColor=555555)
 **SRA-RiskGate-4B checks a stablecoin payment before an AI agent sends it, and answers `approve`, `hold` or `reject`** with reason codes. It is a 4B model, fine-tuned from `Qwen/Qwen3-4B-Instruct-2507`, that runs on a laptop.
 ## 🔌 Use It From an AI Agent (MCP)
+[`sra-riskgate-mcp`](https://pypi.org/project/sra-riskgate-mcp/) gives Claude Desktop, Cursor and other MCP clients eleven tools: nine to call **before** paying, and two to confirm the payment **after** it settles:
 | Tool | What it does | Needs |
 | --- | --- | --- |
 | `check_circle_wallets_request` | The same checks for a Circle Wallets API request (transfer, contract execution, signing) before it is sent to Circle; approvals, raw messages and wallet upgrades are held | Nothing |
 | `check_delegation` | An EIP-7702 authorization before signing: always held, naming the contract and whether it is valid on every chain | Nothing |
 | `check_user_operation` | An ERC-4337 UserOperation from a smart account (Coinbase Smart Wallet, Safe, Kernel, Nexus, SimpleAccount), call by call: an approval hidden in a batch is held, payments to the same payee are summed | Nothing |
+| `verify_settlement` | **After** settlement: the mined receipt must hold exactly the approved USDC payment (payer, payee, amount, and for x402 the approved authorization) | Nothing (you pass the receipt) |
+| `verify_gateway_balances` | **After** a Circle Gateway payment: the payer's balance went down, and the payee's up, by at least the amount | Nothing (you pass the balances) |
 | `check_payment_with_model` | Full review by SRA-RiskGate-4B over your policy, the payment and your verification results | This model served locally (for example with Ollama) |
 ```json