Instructions to use Pype/cue-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Pype/cue-v1 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 Pype/cue-v1:Q8_0
# Run inference directly in the terminal:
llama cli -hf Pype/cue-v1:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Pype/cue-v1:Q8_0
# Run inference directly in the terminal:
llama cli -hf Pype/cue-v1:Q8_0

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 Pype/cue-v1:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf Pype/cue-v1:Q8_0

Use Docker

docker model run hf.co/Pype/cue-v1:Q8_0

Llama new
LM Studio
Jan
Ollama
How to use Pype/cue-v1 with Ollama:
```
ollama run hf.co/Pype/cue-v1:Q8_0
```
Unsloth Desktop

How to use Pype/cue-v1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Pype/cue-v1:Q8_0

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": "Pype/cue-v1:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Pype/cue-v1 with Docker Model Runner:
```
docker model run hf.co/Pype/cue-v1:Q8_0
```

Lemonade

How to use Pype/cue-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Pype/cue-v1:Q8_0

Run and chat with the model

lemonade run user.cue-v1-Q8_0

List all available models

lemonade list

Hermes Agent

How to use Pype/cue-v1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Pype/cue-v1:Q8_0

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 Pype/cue-v1:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Pype/cue-v1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Pype/cue-v1:Q8_0

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 "Pype/cue-v1:Q8_0" \
  --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"

AshishPype commited on 16 days ago

Commit

830c8f5

verified ·

1 Parent(s): 2be3308

Card: GitHub links at the top

Browse files

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -18,6 +18,8 @@ pipeline_tag: text-classification
 # Cue v1
 **Cue v1 is turn detection for voice agents that combines context and audio:**
 > **Cue v1 = the fine-tuned Gemma 4 E4B's logits (the words and context) × √Smart Turn v3.2 (the voice)**
@@ -387,6 +389,7 @@ The base model almost never answers HOLDING. That is the main thing the fine-tun
 | `prompts/end_of_turn_phone.json` | End of turn, caller and agent on a phone call |
 | `prompts/end_of_turn_dialogue.json` | End of turn, two people talking |
 | `prompts/barge_in.json` | Interruptions: STOP or CONTINUE while the agent is speaking |
 | `assets/` | The English table, the 14-language heatmaps and the script that draws them; the Thought Hold demo clip |
 ## Intended use

 # Cue v1
+**[💻 Code on GitHub](https://github.com/PYPE-AI-MAIN/cue-v1)** · **[📊 Full results and analysis](https://github.com/PYPE-AI-MAIN/cue-v1/blob/main/RESULTS.md)** · **[✅ Check our numbers](https://github.com/PYPE-AI-MAIN/cue-v1#check-our-numbers)**
 **Cue v1 is turn detection for voice agents that combines context and audio:**
 > **Cue v1 = the fine-tuned Gemma 4 E4B's logits (the words and context) × √Smart Turn v3.2 (the voice)**
 | `prompts/end_of_turn_phone.json` | End of turn, caller and agent on a phone call |
 | `prompts/end_of_turn_dialogue.json` | End of turn, two people talking |
 | `prompts/barge_in.json` | Interruptions: STOP or CONTINUE while the agent is speaking |
+| Code, benchmark predictions, verification | [github.com/PYPE-AI-MAIN/cue-v1](https://github.com/PYPE-AI-MAIN/cue-v1): the `cue` client, every eot-bench prediction, `verify.py`, `RESULTS.md` |
 | `assets/` | The English table, the 14-language heatmaps and the script that draws them; the Thought Hold demo clip |
 ## Intended use