Instructions to use Verdugie/Fable-Therapy-Lite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Verdugie/Fable-Therapy-Lite 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 Verdugie/Fable-Therapy-Lite:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Verdugie/Fable-Therapy-Lite:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Verdugie/Fable-Therapy-Lite:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Verdugie/Fable-Therapy-Lite: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 Verdugie/Fable-Therapy-Lite:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf Verdugie/Fable-Therapy-Lite:Q4_K_M

Use Docker

docker model run hf.co/Verdugie/Fable-Therapy-Lite:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use Verdugie/Fable-Therapy-Lite with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Verdugie/Fable-Therapy-Lite:Q4_K_M

Ollama
How to use Verdugie/Fable-Therapy-Lite with Ollama:
```
ollama run hf.co/Verdugie/Fable-Therapy-Lite:Q4_K_M
```
Unsloth Desktop

How to use Verdugie/Fable-Therapy-Lite with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Verdugie/Fable-Therapy-Lite: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": "Verdugie/Fable-Therapy-Lite:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Verdugie/Fable-Therapy-Lite with Docker Model Runner:
```
docker model run hf.co/Verdugie/Fable-Therapy-Lite:Q4_K_M
```

Lemonade

How to use Verdugie/Fable-Therapy-Lite with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Verdugie/Fable-Therapy-Lite:Q4_K_M

Run and chat with the model

lemonade run user.Fable-Therapy-Lite-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Verdugie/Fable-Therapy-Lite with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Verdugie/Fable-Therapy-Lite: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 Verdugie/Fable-Therapy-Lite:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Verdugie/Fable-Therapy-Lite with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Verdugie/Fable-Therapy-Lite: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 "Verdugie/Fable-Therapy-Lite: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"

Verdugie commited on 20 days ago

Commit

a483236

verified ·

1 Parent(s): 78436b6

Card: topic coverage in the intro; family chart label

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -34,7 +34,7 @@ From the Greek *therapeía*, "healing, curing" — from *therapeúein*, "to atte
 ## Fable Therapy Lite
-A therapy-style conversational model fine-tuned from Qwen 3.5 4B on **4,537 counseling conversations**. It is the 4B build of the Fable pair, with Fable Therapy as the 9B build. It runs a structured clinical read before every reply and keeps a running **timeline ledger** of the conversation's facts.
 Its training data was written by Opus 4.8 to a standard reverse-engineered from a limited set of Fable 5 samples. No system prompt required.
@@ -177,7 +177,7 @@ Not a clinician, not a crisis service. It doesn't diagnose, treat, or replace pr
 | [Therapy 3.5](https://huggingface.co/Verdugie/Therapy-3.5) | 9B | everyday hardware |
 | [Fable Therapy](https://huggingface.co/Verdugie/Fable-Therapy) | 9B | the 9B build of the Fable pair |
 | **Fable Therapy Lite** (this model) | 4B | the 4B build of the Fable pair |
-| [Opus Therapy](https://huggingface.co/Verdugie/Opus-Therapy) | 9B | Opus-written corpus |
 ## Dataset

 ## Fable Therapy Lite
+A therapy-style conversational model fine-tuned from Qwen 3.5 4B on **4,537 counseling conversations**. It is the 4B build of the Fable pair, with Fable Therapy as the 9B build. It runs a structured clinical read before every reply and keeps a running **timeline ledger** of the conversation's facts. Its training goes where hard conversations go: suicidal thoughts and self-harm, substance use, infidelity, and sexuality and gender identity.
 Its training data was written by Opus 4.8 to a standard reverse-engineered from a limited set of Fable 5 samples. No system prompt required.
 | [Therapy 3.5](https://huggingface.co/Verdugie/Therapy-3.5) | 9B | everyday hardware |
 | [Fable Therapy](https://huggingface.co/Verdugie/Fable-Therapy) | 9B | the 9B build of the Fable pair |
 | **Fable Therapy Lite** (this model) | 4B | the 4B build of the Fable pair |
+| [Opus Therapy](https://huggingface.co/Verdugie/Opus-Therapy) | 9B | extended taboo coverage |
 ## Dataset