Instructions to use Floobin/TSwifty-SN6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Floobin/TSwifty-SN6 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Floobin/TSwifty-SN6") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Floobin/TSwifty-SN6") model = AutoModelForCausalLM.from_pretrained("Floobin/TSwifty-SN6", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Floobin/TSwifty-SN6 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Floobin/TSwifty-SN6" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Floobin/TSwifty-SN6", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Floobin/TSwifty-SN6
- SGLang
How to use Floobin/TSwifty-SN6 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 "Floobin/TSwifty-SN6" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Floobin/TSwifty-SN6", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "Floobin/TSwifty-SN6" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Floobin/TSwifty-SN6", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Floobin/TSwifty-SN6 with Docker Model Runner:
docker model run hf.co/Floobin/TSwifty-SN6
| import base64 | |
| import io | |
| from urllib.parse import unquote | |
| from fsspec import AbstractFileSystem | |
| class DataFileSystem(AbstractFileSystem): | |
| """A handy decoder for data-URLs | |
| Example | |
| ------- | |
| >>> with fsspec.open("data:,Hello%2C%20World%21") as f: | |
| ... print(f.read()) | |
| b"Hello, World!" | |
| """ | |
| protocol = "data" | |
| def __init__(self, **kwargs): | |
| """No parameters for this filesystem""" | |
| super().__init__(**kwargs) | |
| def cat_file(self, path, start=None, end=None, **kwargs): | |
| pref, data = path.split(",", 1) | |
| if pref.endswith("base64"): | |
| return base64.b64decode(data)[start:end] | |
| return unquote(data).encode()[start:end] | |
| def info(self, path, **kwargs): | |
| pref, name = path.split(",", 1) | |
| data = self.cat_file(path) | |
| mime = pref.split(":", 1)[1].split(";", 1)[0] | |
| return {"name": name, "size": len(data), "type": "file", "mimetype": mime} | |
| def _open( | |
| self, | |
| path, | |
| mode="rb", | |
| block_size=None, | |
| autocommit=True, | |
| cache_options=None, | |
| **kwargs, | |
| ): | |
| if "r" not in mode: | |
| raise ValueError("Read only filesystem") | |
| return io.BytesIO(self.cat_file(path)) | |