Instructions to use Floobin/TSwifty-SN6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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
```

TSwifty-SN6 / venv /Lib /site-packages /setuptools /command /install_egg_info.py

Floobin

Upload folder using huggingface_hub

0a594a8 verified over 2 years ago

Raw

History Blame Contribute Delete

2.2 kB

	from distutils import log, dir_util
	import os

	from setuptools import Command
	from setuptools import namespaces
	from setuptools.archive_util import unpack_archive
	import pkg_resources


	class install_egg_info(namespaces.Installer, Command):
	"""Install an .egg-info directory for the package"""

	description = "Install an .egg-info directory for the package"

	user_options = [
	('install-dir=', 'd', "directory to install to"),
	]

	def initialize_options(self):
	self.install_dir = None

	def finalize_options(self):
	self.set_undefined_options('install_lib',
	('install_dir', 'install_dir'))
	ei_cmd = self.get_finalized_command("egg_info")
	basename = pkg_resources.Distribution(
	None, None, ei_cmd.egg_name, ei_cmd.egg_version
	).egg_name() + '.egg-info'
	self.source = ei_cmd.egg_info
	self.target = os.path.join(self.install_dir, basename)
	self.outputs = []

	def run(self):
	self.run_command('egg_info')
	if os.path.isdir(self.target) and not os.path.islink(self.target):
	dir_util.remove_tree(self.target, dry_run=self.dry_run)
	elif os.path.exists(self.target):
	self.execute(os.unlink, (self.target,), "Removing " + self.target)
	if not self.dry_run:
	pkg_resources.ensure_directory(self.target)
	self.execute(
	self.copytree, (), "Copying %s to %s" % (self.source, self.target)
	)
	self.install_namespaces()

	def get_outputs(self):
	return self.outputs

	def copytree(self):
	# Copy the .egg-info tree to site-packages
	def skimmer(src, dst):
	# filter out source-control directories; note that 'src' is always
	# a '/'-separated path, regardless of platform. 'dst' is a
	# platform-specific path.
	for skip in '.svn/', 'CVS/':
	if src.startswith(skip) or '/' + skip in src:
	return None
	self.outputs.append(dst)
	log.debug("Copying %s to %s", src, dst)
	return dst

	unpack_archive(self.source, self.target, skimmer)