Instructions to use arenard/Formatter-2-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arenard/Formatter-2-1.5B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="arenard/Formatter-2-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("arenard/Formatter-2-1.5B")
model = AutoModelForCausalLM.from_pretrained("arenard/Formatter-2-1.5B", 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 arenard/Formatter-2-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arenard/Formatter-2-1.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arenard/Formatter-2-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/arenard/Formatter-2-1.5B

SGLang

How to use arenard/Formatter-2-1.5B 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 "arenard/Formatter-2-1.5B" \
    --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": "arenard/Formatter-2-1.5B",
		"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 "arenard/Formatter-2-1.5B" \
        --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": "arenard/Formatter-2-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use arenard/Formatter-2-1.5B 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 arenard/Formatter-2-1.5B 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 arenard/Formatter-2-1.5B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for arenard/Formatter-2-1.5B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="arenard/Formatter-2-1.5B",
    max_seq_length=2048,
)

Docker Model Runner
How to use arenard/Formatter-2-1.5B with Docker Model Runner:
```
docker model run hf.co/arenard/Formatter-2-1.5B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Prompt

user_prompt = """You will receive a block of unformatted or poorly formatted text. Your task is to rewrite this text with correct formatting, adjusting only the spaces and line breaks (\\n) to make it readable and well-structured. Do not modify any characters other than whitespace.

All words, punctuation, and letter casing must remain exactly the same.

Some inputs may contain no spaces or line breaks at all. Reconstruct the text as best as possible based on natural language structure and punctuation cues.

Only return the reformatted text. Do not add any explanations or comments.

Text to format:
<TEXT>
Your text here.
</TEXT>"""

# When the chat template is applied:
"<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n<|im_start|>user\nYou will receive a block of unformatted or poorly formatted text. Your task is to rewrite this text with correct formatting, adjusting only the spaces and line breaks (\\n) to make it readable and well-structured. Do not modify any characters other than whitespace.\n\nAll words, punctuation, and letter casing must remain exactly the same.\n\nSome inputs may contain no spaces or line breaks at all. Reconstruct the text as best as possible based on natural language structure and punctuation cues.\n\nOnly return the reformatted text. Do not add any explanations or comments.\n\nText to format:\n<TEXT>\nYour text here.\n</TEXT><|im_end|>\n<|im_start|>assistant\n"