Text Generation
Safetensors
GGUF
English
qwen3_5
twinkie
child-safety
education
unsloth
qwen
lora
conversational
Instructions to use Cyrax321/twinkie-2b 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 Cyrax321/twinkie-2b 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 Cyrax321/twinkie-2b:Q4_K_M # Run inference directly in the terminal: llama cli -hf Cyrax321/twinkie-2b:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Cyrax321/twinkie-2b:Q4_K_M # Run inference directly in the terminal: llama cli -hf Cyrax321/twinkie-2b: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 Cyrax321/twinkie-2b:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf Cyrax321/twinkie-2b:Q4_K_M
Use Docker
docker model run hf.co/Cyrax321/twinkie-2b:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use Cyrax321/twinkie-2b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Cyrax321/twinkie-2b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Cyrax321/twinkie-2b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Cyrax321/twinkie-2b:Q4_K_M
- Ollama
How to use Cyrax321/twinkie-2b with Ollama:
ollama run hf.co/Cyrax321/twinkie-2b:Q4_K_M
- Unsloth Desktop
- Pi
How to use Cyrax321/twinkie-2b with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Cyrax321/twinkie-2b: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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Cyrax321/twinkie-2b:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Cyrax321/twinkie-2b with Docker Model Runner:
docker model run hf.co/Cyrax321/twinkie-2b:Q4_K_M
- Lemonade
How to use Cyrax321/twinkie-2b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Cyrax321/twinkie-2b:Q4_K_M
Run and chat with the model
lemonade run user.twinkie-2b-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Cyrax321/twinkie-2b with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Cyrax321/twinkie-2b: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://127.0.0.1:9931/v1 hermes config set model.default Cyrax321/twinkie-2b:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Cyrax321/twinkie-2b with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Cyrax321/twinkie-2b: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://127.0.0.1:9931/v1 \ --custom-model-id "Cyrax321/twinkie-2b: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"
Commit History
15 days ago
-
Add training curves, comparison diagram, and evaluation metrics to model card
Verified signature5deeea7 -
Rename GGUF files to twinkie-2b
Verified signaturec5d481b -
Update README.md
Verified signature8b3baa1 -
Add training curves, comparison diagram, and evaluation metrics to model card
Verified signature4d4874d -
Embed training curves, comparison diagram, and evaluation metrics in model card
Verified signature86eeccd -
Add Twinkie-2B official model card
Verified signature1718c90 -
Add artifact: eval_outputs.csv
Verified signature80473e3 -
Add artifact: twinkie_evalset.py
Verified signature75b4afb -
Add artifact: comparison.csv
Verified signature0d39cd3 -
Add artifact: manifest.json
Verified signaturee77634d -
Add artifact: review_sheet.csv
Verified signature886747f -
Add artifact: gate_report.json
Verified signature219bf29 -
Add artifact: twinkie_safety.py
Verified signature02552fc -
Add artifact: train.jsonl
Verified signature06286f7 -
Add artifact: test_twinkie.py
Verified signature107106f -
Add artifact: twinkie_core.py
Verified signature8568102 -
Add artifact: metrics_report.json
Verified signature1271795 -
Add artifact: val.jsonl
Verified signature88460f1 -
Add artifact: training_curves.png
Verified signature27c2b6a -
Add artifact: comparison_diagram.png
Verified signature4852735 -
Add artifact: events.jsonl
Verified signaturea52fa78 -
Add artifact: twinkie_data.py
Verified signaturecfcdde4 -
Add GGUF quant Qwen3.5-2B.F16-mmproj.gguf
Verified signatureae2e151 -
Add GGUF quant Qwen3.5-2B.Q8_0.gguf
Verified signatureb0e354f -
Add GGUF quant Qwen3.5-2B.Q4_K_M.gguf
Verified signaturec3bd781 -
Add GGUF quant Qwen3.5-2B.F16-mmproj.gguf
Verified signatureabf263e -
Add Twinkie-2B LoRA adapter
Verified signatureb6e6897 -
Add Twinkie-2B 16-bit merged model weights
Verified signaturebff5cc1 -
initial commit
Verified signatureec596d0