Instructions to use calebboud/vibescript 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 calebboud/vibescript 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 calebboud/vibescript:Q4_K_M # Run inference directly in the terminal: llama cli -hf calebboud/vibescript:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf calebboud/vibescript:Q4_K_M # Run inference directly in the terminal: llama cli -hf calebboud/vibescript: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 calebboud/vibescript:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf calebboud/vibescript: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 calebboud/vibescript:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf calebboud/vibescript:Q4_K_M
Use Docker
docker model run hf.co/calebboud/vibescript:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use calebboud/vibescript with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "calebboud/vibescript" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "calebboud/vibescript", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/calebboud/vibescript:Q4_K_M
- Ollama
How to use calebboud/vibescript with Ollama:
ollama run hf.co/calebboud/vibescript:Q4_K_M
- Unsloth Studio
How to use calebboud/vibescript 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 calebboud/vibescript 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 calebboud/vibescript to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for calebboud/vibescript to start chatting
- Pi
How to use calebboud/vibescript with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf calebboud/vibescript: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": "calebboud/vibescript:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use calebboud/vibescript with Docker Model Runner:
docker model run hf.co/calebboud/vibescript:Q4_K_M
- Lemonade
How to use calebboud/vibescript with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull calebboud/vibescript:Q4_K_M
Run and chat with the model
lemonade run user.vibescript-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use calebboud/vibescript with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf calebboud/vibescript: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 calebboud/vibescript:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use calebboud/vibescript with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf calebboud/vibescript: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 "calebboud/vibescript: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"
VibeScript - Code to DSL Converter
vibecoder-discern converts natural language and code into VibeScript - a compact symbolic DSL for expressing programming concepts.
What is VibeScript?
VibeScript compresses verbose code into symbolic notation:
| Code | VibeScript |
|---|---|
function add(a, b) { return a + b; } |
ฮฉ> add!(a, b) |
const users = await db.query(...) |
ฮด.m.p.query() |
app.get('/api/users', ...) |
ฮธ.m.route(ฮธ.e, ฮถ.x) |
if (error) { throw new Error(...) } |
~system~ฮณ#error! |
Model Variants
| Path | Format | Size | Use Case |
|---|---|---|---|
/lora-adapter/ |
LoRA | ~13MB | Merge with your own Qwen3-1.7B |
/merged-model/ |
HuggingFace | ~3.4GB | Ready-to-use transformers |
/gguf/ |
GGUF Q4_K_M | ~1.1GB | llama.cpp / Ollama |
Quick Start
llama.cpp (GGUF)
# Download
wget https://huggingface.co/calebboud/vibescript/resolve/main/gguf/vibecoder-discern-1.7B-Q4_K_M.gguf
# Run
llama-cli -m vibecoder-discern-1.7B-Q4_K_M.gguf \
-p "Convert this to vibescript: function multiply(x, y) { return x * y; }" \
-n 100 --temp 0.7
Transformers (Merged Model)
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("calebboud/vibescript", subfolder="merged-model")
tokenizer = AutoTokenizer.from_pretrained("calebboud/vibescript", subfolder="merged-model")
prompt = "Convert this to vibescript: console.log('Hello World')"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
LoRA Adapter (Merge Yourself)
from peft import PeftModel
from transformers import AutoModelForCausalLM
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-1.7B")
model = PeftModel.from_pretrained(base, "calebboud/vibescript", subfolder="lora-adapter")
merged = model.merge_and_unload()
Training Details
- Base Model: Qwen/Qwen3-1.7B
- Method: LoRA (r=8, alpha=16)
- Target Modules: q_proj, k_proj, v_proj, o_proj
- Dataset: 885 code โ vibescript examples
- Task: CAUSAL_LM
VibeScript Symbols
| Symbol | Meaning |
|---|---|
ฮฉ> |
Function definition |
ฮฃ |
Route/scaffold |
ฮด |
Database operations |
ฮธ |
HTTP/API |
ฮณ |
Error handling |
ฮถ |
Structure/scaffold |
ฮฑ |
Analysis |
ฮต |
Dependencies |
Coming Soon
- vibecoder-expand: VibeScript โ Code (reverse direction)
License
Apache 2.0
- Downloads last month
- 2
Hardware compatibility
Log In to add your hardware
4-bit