Instructions to use Chinook416/caracat_code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Chinook416/caracat_code with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Chinook416/caracat_code")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Chinook416/caracat_code", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Chinook416/caracat_code with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Chinook416/caracat_code" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Chinook416/caracat_code", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Chinook416/caracat_code
- SGLang
How to use Chinook416/caracat_code with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Chinook416/caracat_code" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Chinook416/caracat_code", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Chinook416/caracat_code" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Chinook416/caracat_code", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Chinook416/caracat_code with Docker Model Runner:
docker model run hf.co/Chinook416/caracat_code
| Caracat Code | |
| Copyright 2026 Caracat Code Project | |
| This product includes software developed by the Caracat Code Project. | |
| ================================================================================ | |
| Base model attribution | |
| ================================================================================ | |
| Caracat Code is based on Qwen3-Coder-Next by Qwen. | |
| Upstream model Qwen/Qwen3-Coder-Next | |
| Upstream URL https://huggingface.co/Qwen/Qwen3-Coder-Next | |
| Upstream license Apache License 2.0, as listed on the Hugging Face model | |
| page. See THIRD_PARTY_LICENSES.md for the current | |
| verification status of this statement. | |
| Caracat Code was not trained from scratch. It derives from the upstream model | |
| named above. | |
| Any copyright notices, license notices, NOTICE files and attribution | |
| information distributed with the upstream model must be preserved in every | |
| redistribution of that material, including redistribution in modified form, as | |
| required by the Apache License 2.0. | |
| ================================================================================ | |
| Scope of this NOTICE | |
| ================================================================================ | |
| The Apache License 2.0 in the LICENSE file of this repository applies to the | |
| original source code authored for this project (training tooling, evaluation | |
| tooling, configuration and documentation in this repository). | |
| It does not, by itself, grant any rights in the upstream model weights. Those | |
| remain governed by the license under which Qwen distributes them. | |
| Third-party components and their licenses are listed in | |
| THIRD_PARTY_LICENSES.md. | |