Instructions to use frameprotocol/frame-intent-english with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use frameprotocol/frame-intent-english with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="frameprotocol/frame-intent-english",
	filename="model.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use frameprotocol/frame-intent-english with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf frameprotocol/frame-intent-english
# Run inference directly in the terminal:
llama-cli -hf frameprotocol/frame-intent-english

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf frameprotocol/frame-intent-english
# Run inference directly in the terminal:
llama-cli -hf frameprotocol/frame-intent-english

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf frameprotocol/frame-intent-english
# Run inference directly in the terminal:
./llama-cli -hf frameprotocol/frame-intent-english

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf frameprotocol/frame-intent-english
# Run inference directly in the terminal:
./build/bin/llama-cli -hf frameprotocol/frame-intent-english

Use Docker

docker model run hf.co/frameprotocol/frame-intent-english

LM Studio
Jan

vLLM

How to use frameprotocol/frame-intent-english with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/frameprotocol/frame-intent-english

Ollama
How to use frameprotocol/frame-intent-english with Ollama:
```
ollama run hf.co/frameprotocol/frame-intent-english
```

Unsloth Studio new

How to use frameprotocol/frame-intent-english with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for frameprotocol/frame-intent-english to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for frameprotocol/frame-intent-english to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for frameprotocol/frame-intent-english to start chatting

Pi new

How to use frameprotocol/frame-intent-english with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf frameprotocol/frame-intent-english

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "frame-intent-english"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use frameprotocol/frame-intent-english with Docker Model Runner:
```
docker model run hf.co/frameprotocol/frame-intent-english
```

Lemonade

How to use frameprotocol/frame-intent-english with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull frameprotocol/frame-intent-english

Run and chat with the model

lemonade run user.frame-intent-english-{{QUANT_TAG}}

List all available models

lemonade list

FRAME NL → Intent Compiler (English)

This model converts natural language into structured intent JSON:

{ "intent": "string", "params": { "key": "value" } }

Important:

The model is NOT trusted for correctness
Runtime MUST enforce substring validation
Runtime MUST compute missing params

Example:

Input: send bob hello

Output: { "intent": "message.send", "params": { "to": "bob", "text": "hello" } }

Note: this is not perfect for a reason, frames runtime will fix it entirely over time

Run locally (llama.cpp)

Requirements: llama.cpp built (llama-cli binary available)

Example:

git clone https://huggingface.co/frameprotocol/frame-intent-english

/path/to/llama-cli \
  -m model.gguf \
  -p "send bob 5 dollars" \
  -n 100 \
  --temp 0.0

Expected output (approx):

{"intent":"payment.send","params":{"to":"bob","text":"5"}}

Run with validation (this repo):

python infer.py "send bob 5 dollars"

Expected output:

{"intent":"payment.send","params":{"to":"bob"}}

Notes:

Output is strict JSON only
Params not present in input are removed by validation

How it works

flowchart LR
    A[Natural language input] --> B[GGUF model\nllama-cli]
    B --> C[Raw JSON output]
    C --> D[Validation\ninfer.py]
    D --> E[Cleaned intent JSON]

Downloads last month: 3

GGUF

Model size

0.2B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants