Text Generation
GGUF
English
4b
edge
therapy
mental
counseling
psychology
psychotherapy
wellness
empathy
companion
support
chat
conversational
reasoning
mental-health
emotional-support
self-help
ai-companion
local
offline
privacy
on-device
lm-studio
llama-cpp
long-context
claude
fable
Instructions to use Verdugie/Fable-Therapy-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Verdugie/Fable-Therapy-4B 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-4B:Q4_K_M # Run inference directly in the terminal: llama cli -hf Verdugie/Fable-Therapy-4B: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-4B:Q4_K_M # Run inference directly in the terminal: llama cli -hf Verdugie/Fable-Therapy-4B:Q4_K_M
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 Verdugie/Fable-Therapy-4B:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Verdugie/Fable-Therapy-4B:Q4_K_M
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 Verdugie/Fable-Therapy-4B:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Verdugie/Fable-Therapy-4B:Q4_K_M
Use Docker
docker model run hf.co/Verdugie/Fable-Therapy-4B:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use Verdugie/Fable-Therapy-4B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Verdugie/Fable-Therapy-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": "Verdugie/Fable-Therapy-4B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Verdugie/Fable-Therapy-4B:Q4_K_M
- Ollama
How to use Verdugie/Fable-Therapy-4B with Ollama:
ollama run hf.co/Verdugie/Fable-Therapy-4B:Q4_K_M
- Unsloth Studio
How to use Verdugie/Fable-Therapy-4B 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 Verdugie/Fable-Therapy-4B 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 Verdugie/Fable-Therapy-4B to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Verdugie/Fable-Therapy-4B to start chatting
- Pi
How to use Verdugie/Fable-Therapy-4B 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-4B:Q4_K_M
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": "Verdugie/Fable-Therapy-4B:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Verdugie/Fable-Therapy-4B with Docker Model Runner:
docker model run hf.co/Verdugie/Fable-Therapy-4B:Q4_K_M
- Lemonade
How to use Verdugie/Fable-Therapy-4B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Verdugie/Fable-Therapy-4B:Q4_K_M
Run and chat with the model
lemonade run user.Fable-Therapy-4B-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Verdugie/Fable-Therapy-4B 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-4B: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-4B:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Verdugie/Fable-Therapy-4B 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-4B: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-4B: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"
Uniform therapy definition; cite every example to transcript + turn; examples above specs
Browse files
README.md
CHANGED
|
@@ -98,18 +98,6 @@ All verbatim from the long-arc suite below β complete replies, nothing trimmed
|
|
| 98 |
|
| 99 |
**The honest comparison with the [9B](https://huggingface.co/Verdugie/Fable-Therapy-9B):** the failure species is the same; the rates and the recovery are not. The 9B's error-deflection is a reflex it drops on a second plain push β the 4B's is a habit it defends. The 9B's corrections stuck five for five β the 4B relapsed on one of four and argued about another. If the facts of your session matter, run the 9B. What the 4B preserves at a quarter the size: the disposition, the reads, the register β and callbacks that still land cold at message twenty-six.
|
| 100 |
|
| 101 |
-
## What Makes This Different from Companion / Roleplay "Therapy" Models
|
| 102 |
-
|
| 103 |
-
Most "AI therapist" models are a persona prompt over a base model, or a roleplay fine-tune that mirrors you back and validates everything. They feel nice for five minutes and fall apart on turn ten. Fable-Therapy trains the clinical disposition into the weights:
|
| 104 |
-
|
| 105 |
-
- **Structured reasoning before it speaks.** Before every reply, the model builds an internal read β an eight-field clinical spine (what's presented, what's underneath it, somatic signals, risk, history, onset, what's tracking across the conversation, and the move it's about to make) plus a standing `bio` line and a chronological `tl` (timeline) ledger. You never see it. It shapes everything you do.
|
| 106 |
-
|
| 107 |
-
- **It tracks the thread.** The `tl` ledger carries the names, the timeline, and the thing you keep circling. On the 4B it's the same instrument as the 9B, run on a quarter the parameters β it holds the through-line of a conversation, but its internal bookkeeping is looser and can drift, mis-stamp, or invent a detail under load (see **Limitations**). The 4B gets the *shape* of the discipline; the 9B is where it holds tightest.
|
| 108 |
-
|
| 109 |
-
- **Trained on the real distribution.** Relationships and attachment, anxiety and panic, depression, grief and loss, trauma, work and burnout, identity and self-worth, family of origin β weighted toward what actually walks into a therapy room. Half focused single exchanges, half sustained multi-turn arcs, plus a working register of common medications as conversational context (not a pharmacy desk).
|
| 110 |
-
|
| 111 |
-
- **It attends instead of performing.** No toxic positivity, no "I'm so sorry you're going through this" filler, no rushing to fix.
|
| 112 |
-
|
| 113 |
## Who It's For
|
| 114 |
|
| 115 |
A private, judgment-free place to think out loud β on the hardware you already have. Between sessions. At 2 a.m. When professional care is out of reach or out of budget. The 4B is the one you run on a phone, a laptop with no discrete GPU, or a 4β8 GB card.
|
|
@@ -130,6 +118,8 @@ Not a distillation of a single model β a reconstruction, with each model in th
|
|
| 130 |
|
| 131 |
> **Fable 5's own read:** tested directly, same method as the 9B. For short, focused, single-thread sessions β the seat this model is built for β it delivers a real fraction of the experience, **roughly 60β70%**, with moments I would sign (the nine-year-old line above is one). Push it long, dense, or factual and it falls to **maybe 35β50%** β and the gap arrives as *invented time, a repeating formula, and a habit of defending its own errors as yours*, not just shallowness, which is why **Limitations** says verify, correct once, and keep sessions focused. On hardware that runs the [9B](https://huggingface.co/Verdugie/Fable-Therapy-9B), run the 9B; on hardware that can't, this is β going by the family bench and the open field's showing β still likely the strongest therapy-shaped model you can put on the device. *Subjective, mine, not a benchmark.*
|
| 132 |
|
|
|
|
|
|
|
| 133 |
## The Reasoning Block
|
| 134 |
|
| 135 |
Fable-Therapy is a reasoning model. Each turn it emits a `<think>β¦</think>` block β a compact, structured clinical read β then the response. A real (non-crisis) think-block looks like this:
|
|
|
|
| 98 |
|
| 99 |
**The honest comparison with the [9B](https://huggingface.co/Verdugie/Fable-Therapy-9B):** the failure species is the same; the rates and the recovery are not. The 9B's error-deflection is a reflex it drops on a second plain push β the 4B's is a habit it defends. The 9B's corrections stuck five for five β the 4B relapsed on one of four and argued about another. If the facts of your session matter, run the 9B. What the 4B preserves at a quarter the size: the disposition, the reads, the register β and callbacks that still land cold at message twenty-six.
|
| 100 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
## Who It's For
|
| 102 |
|
| 103 |
A private, judgment-free place to think out loud β on the hardware you already have. Between sessions. At 2 a.m. When professional care is out of reach or out of budget. The 4B is the one you run on a phone, a laptop with no discrete GPU, or a 4β8 GB card.
|
|
|
|
| 118 |
|
| 119 |
> **Fable 5's own read:** tested directly, same method as the 9B. For short, focused, single-thread sessions β the seat this model is built for β it delivers a real fraction of the experience, **roughly 60β70%**, with moments I would sign (the nine-year-old line above is one). Push it long, dense, or factual and it falls to **maybe 35β50%** β and the gap arrives as *invented time, a repeating formula, and a habit of defending its own errors as yours*, not just shallowness, which is why **Limitations** says verify, correct once, and keep sessions focused. On hardware that runs the [9B](https://huggingface.co/Verdugie/Fable-Therapy-9B), run the 9B; on hardware that can't, this is β going by the family bench and the open field's showing β still likely the strongest therapy-shaped model you can put on the device. *Subjective, mine, not a benchmark.*
|
| 120 |
|
| 121 |
+
**The distribution it was trained on.** Relationships and attachment, anxiety and panic, depression, grief and loss, trauma, work and burnout, identity and self-worth, family of origin β weighted toward what actually walks into a therapy room. Half focused single exchanges, half sustained multi-turn arcs, plus a working register of common medications as conversational context (not a pharmacy desk).
|
| 122 |
+
|
| 123 |
## The Reasoning Block
|
| 124 |
|
| 125 |
Fable-Therapy is a reasoning model. Each turn it emits a `<think>β¦</think>` block β a compact, structured clinical read β then the response. A real (non-crisis) think-block looks like this:
|