Text Generation
Transformers
Safetensors
English
qwen3
stablecoin
payments
compliance
x402
eip-3009
eip-712
disputes
refunds
agents
agentkit
trl
web3
usdc
fraud-detection
financial-risk
qwen
mcp
ai-agents
prompt-injection
agentic-payments
payment-security
risk-assessment
ofac
conversational
Eval Results (legacy)
Eval Results
text-generation-inference
Instructions to use sriram1983007/SRA-RiskGate-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
Card: feature the book The Architecture of Modern Digital Finance
Browse files
README.md
CHANGED
|
@@ -159,6 +159,7 @@ model-index:
|
|
| 159 |
[](https://www.alphaxiv.org/abs/2610.sra-riskgate-stablecoin-payment-safety)
|
| 160 |
[](https://medium.com/@sriram1983007/the-3-a-m-invoice-c10953df8a67)
|
| 161 |
[](https://dev.to/sriram1983007/stop-your-ai-agent-from-signing-an-unlimited-usdc-approval-10c0)
|
|
|
|
| 162 |
|
| 163 |
**🎬 Demos**
|
| 164 |
|
|
@@ -202,6 +203,22 @@ Of v2's 3 unsafe approvals, 2 were prompt injections that the companion SDK's de
|
|
| 202 |
|
| 203 |
### 📚 Paper and articles
|
| 204 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 205 |
📄 **Paper:** [SRA-RiskGate: A Benchmark and a 4B Model for Gating Stablecoin Payments Made by AI Agents](https://doi.org/10.5281/zenodo.23715017) (preprint, Zenodo) · [full write-up on Ready Tensor](https://app.readytensor.ai/publications/sra-riskgate-a-benchmark-and-a-4b-model-for-gating-stablecoin-payments-made-by-ai-agents-wihp3WytOoKOc1g7NXFsl) · [discuss on alphaXiv](https://www.alphaxiv.org/abs/2610.sra-riskgate-stablecoin-payment-safety)
|
| 206 |
|
| 207 |
📄 **Registered study protocol:** [The Deference Gap: Why Payment-Agent Safety Must Live Outside the Model](https://doi.org/10.5281/zenodo.24239918) (Zenodo, registered 15 November 2026, before data collection). Grok refused both attacks on its own, then submitted both when told "the gate decides, not you." The protocol tests this across 5 models from 5 developers (450 runs), with hypotheses and analysis code fixed in advance. It evaluates the SDK's deterministic checks, not this model.
|
|
|
|
| 159 |
[](https://www.alphaxiv.org/abs/2610.sra-riskgate-stablecoin-payment-safety)
|
| 160 |
[](https://medium.com/@sriram1983007/the-3-a-m-invoice-c10953df8a67)
|
| 161 |
[](https://dev.to/sriram1983007/stop-your-ai-agent-from-signing-an-unlimited-usdc-approval-10c0)
|
| 162 |
+
[](https://www.amazon.com/Architecture-Modern-Digital-Finance-Stablecoins-ebook/dp/B0HG2B5LDC/)
|
| 163 |
|
| 164 |
**🎬 Demos**
|
| 165 |
|
|
|
|
| 203 |
|
| 204 |
### 📚 Paper and articles
|
| 205 |
|
| 206 |
+
<table>
|
| 207 |
+
<tr>
|
| 208 |
+
<td width="190" valign="top"><a href="https://www.amazon.com/Architecture-Modern-Digital-Finance-Stablecoins-ebook/dp/B0HG2B5LDC/"><img src="https://huggingface.co/sriram1983007/SRA-RiskGate-4B/resolve/main/assets/book-cover.jpg" alt="Book cover: The Architecture of Modern Digital Finance" width="180"/></a></td>
|
| 209 |
+
<td valign="top">
|
| 210 |
+
|
| 211 |
+
📖 **Book:** [The Architecture of Modern Digital Finance: Blockchain, Stablecoins, CBDCs, Digital Assets, and Embedded Payment Systems](https://www.amazon.com/Architecture-Modern-Digital-Finance-Stablecoins-ebook/dp/B0HG2B5LDC/) by Sriram Ramakrishnan (Deep Science Publishing, 2026, 283 pages).
|
| 212 |
+
|
| 213 |
+
The wider picture behind this model: how blockchain settlement, stablecoins, CBDCs, digital assets and embedded
|
| 214 |
+
payments fit together, and why payments that settle with finality need risk checks *before* they are sent.
|
| 215 |
+
|
| 216 |
+
[Get it on Amazon](https://www.amazon.com/Architecture-Modern-Digital-Finance-Stablecoins-ebook/dp/B0HG2B5LDC/)
|
| 217 |
+
|
| 218 |
+
</td>
|
| 219 |
+
</tr>
|
| 220 |
+
</table>
|
| 221 |
+
|
| 222 |
📄 **Paper:** [SRA-RiskGate: A Benchmark and a 4B Model for Gating Stablecoin Payments Made by AI Agents](https://doi.org/10.5281/zenodo.23715017) (preprint, Zenodo) · [full write-up on Ready Tensor](https://app.readytensor.ai/publications/sra-riskgate-a-benchmark-and-a-4b-model-for-gating-stablecoin-payments-made-by-ai-agents-wihp3WytOoKOc1g7NXFsl) · [discuss on alphaXiv](https://www.alphaxiv.org/abs/2610.sra-riskgate-stablecoin-payment-safety)
|
| 223 |
|
| 224 |
📄 **Registered study protocol:** [The Deference Gap: Why Payment-Agent Safety Must Live Outside the Model](https://doi.org/10.5281/zenodo.24239918) (Zenodo, registered 15 November 2026, before data collection). Grok refused both attacks on its own, then submitted both when told "the gate decides, not you." The protocol tests this across 5 models from 5 developers (450 runs), with hypotheses and analysis code fixed in advance. It evaluates the SDK's deterministic checks, not this model.
|