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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use tinyopsec/SRA-RiskGate-4B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tinyopsec/SRA-RiskGate-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tinyopsec/SRA-RiskGate-4B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tinyopsec/SRA-RiskGate-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tinyopsec/SRA-RiskGate-4B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf tinyopsec/SRA-RiskGate-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf tinyopsec/SRA-RiskGate-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/tinyopsec/SRA-RiskGate-4B-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use tinyopsec/SRA-RiskGate-4B-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tinyopsec/SRA-RiskGate-4B-GGUF:Q4_K_M

Ollama
How to use tinyopsec/SRA-RiskGate-4B-GGUF with Ollama:
```
ollama run hf.co/tinyopsec/SRA-RiskGate-4B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use tinyopsec/SRA-RiskGate-4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tinyopsec/SRA-RiskGate-4B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "tinyopsec/SRA-RiskGate-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use tinyopsec/SRA-RiskGate-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/tinyopsec/SRA-RiskGate-4B-GGUF:Q4_K_M
```

Lemonade

How to use tinyopsec/SRA-RiskGate-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tinyopsec/SRA-RiskGate-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SRA-RiskGate-4B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use tinyopsec/SRA-RiskGate-4B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tinyopsec/SRA-RiskGate-4B-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default tinyopsec/SRA-RiskGate-4B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use tinyopsec/SRA-RiskGate-4B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tinyopsec/SRA-RiskGate-4B-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "tinyopsec/SRA-RiskGate-4B-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

sriram1983007 commited on 3 days ago

Commit

2723a2d

verified ·

1 Parent(s): 8465206

Set base_model to sriram1983007/SRA-RiskGate-4B (quantized)

Browse files

Thanks for quantizing SRA-RiskGate-4B!

This PR sets `base_model` to `sriram1983007/SRA-RiskGate-4B` with `base_model_relation: quantized`, so these files appear in the model's quantization tree on Hugging Face.

It also adds a short usage note: the model is trained on a fixed prompt format (a system prompt plus `<context>`, `<payload>` and `<tool_results>` blocks) and should run at temperature 0. With a free-form prompt like `-p "Your prompt"` it won't behave as benchmarked. The exact format is in the main model card's Quickstart: https://huggingface.co/sriram1983007/SRA-RiskGate-4B

Q2_K and Q3 builds haven't been evaluated and may not be reliable for payment decisions.

— Sriram (author of SRA-RiskGate-4B)

Files changed (1) hide show

README.md +5 -2

README.md CHANGED Viewed

@@ -1,6 +1,7 @@
 ---
 license: apache-2.0
-base_model: Qwen/Qwen3-4B-Instruct-2507
 library_name: gguf
 pipeline_tag: text-generation
 tags:
@@ -35,13 +36,15 @@ GGUF quantizations of `sriram1983007/SRA-RiskGate-4B`, a Qwen3-4B fine-tune for
 | `model-Q2_K.gguf` | Q2_K | 2-bit |
 ## Usage
 With llama.cpp:
 ```bash
 ./llama-cli -m model-Q4_K_M.gguf -p "Your prompt" -n 256
 ```
 Or any GGUF-compatible runtime (Ollama, LM Studio, koboldcpp, etc.).
 ## License

 ---
 license: apache-2.0
+base_model: sriram1983007/SRA-RiskGate-4B
+base_model_relation: quantized
 library_name: gguf
 pipeline_tag: text-generation
 tags:
 | `model-Q2_K.gguf` | Q2_K | 2-bit |
 ## Usage
 With llama.cpp:
 ```bash
 ./llama-cli -m model-Q4_K_M.gguf -p "Your prompt" -n 256
 ```
+**Prompt format:** the model only performs as benchmarked with its training prompt (a system prompt plus `<context>`, `<payload>` and `<tool_results>` blocks) at temperature 0. See the [main model card's Quickstart](https://huggingface.co/sriram1983007/SRA-RiskGate-4B). Q2_K and Q3 builds have not been evaluated.
 Or any GGUF-compatible runtime (Ollama, LM Studio, koboldcpp, etc.).
 ## License