Instructions to use qingy2024/Formatter-0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qingy2024/Formatter-0.6B with Transformers:

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

pipe = pipeline("text-generation", model="qingy2024/Formatter-0.6B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("qingy2024/Formatter-0.6B")
model = AutoModelForCausalLM.from_pretrained("qingy2024/Formatter-0.6B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use qingy2024/Formatter-0.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qingy2024/Formatter-0.6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qingy2024/Formatter-0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/qingy2024/Formatter-0.6B

SGLang

How to use qingy2024/Formatter-0.6B 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 "qingy2024/Formatter-0.6B" \
    --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": "qingy2024/Formatter-0.6B",
		"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 "qingy2024/Formatter-0.6B" \
        --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": "qingy2024/Formatter-0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use qingy2024/Formatter-0.6B 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 qingy2024/Formatter-0.6B 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 qingy2024/Formatter-0.6B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for qingy2024/Formatter-0.6B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="qingy2024/Formatter-0.6B",
    max_seq_length=2048,
)

Docker Model Runner
How to use qingy2024/Formatter-0.6B with Docker Model Runner:
```
docker model run hf.co/qingy2024/Formatter-0.6B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Formatter 0.6B

Developed by: qingy2024
License: apache-2.0
Finetuned from model : Qwen3 0.6B (base)

This is mainly my experiment to play around with adding special tokens and changing the chat template while fine-tuning.

{%- set last_message = messages[-1] -%}
{%- if last_message.role == "user" -%}
{{- '<|problem_start|>\n' + last_message.content + '<|problem_end|>\n' -}}
{%- elif last_message.role == "assistant" -%}
{%- for message in messages -%}
{%- if message.role == "user" -%}
{{- '<|problem_start|>\n' + message.content + '<|problem_end|>\n' -}}
{%- elif message.role == "assistant" -%}
{{- '<|formatted_problem_start|>\n' + message.content + '<|formatted_problem_end|>\n' -}}
{%- else -%}
{{- raise('Unknown role: ' + message.role) -}}
{%- endif -%}
{%- endfor -%}
{%- else -%}
{{- raise('Unsupported role: ' + last_message.role) -}}
{%- endif -%}
{%- if add_generation_prompt and last_message.role == "user" -%}
{{- '<|formatted_problem_start|>\n' -}}
{%- endif -%}

Example:

User: Read the excerpt from Dr. Martin Luther King Jr.’s "I Have a Dream" speech.

I am not unmindful that some of you have come here out of great trials and tribulations. Some of you have come fresh from narrow jail cells. Some of you have come from areas where your quest for freedom left you battered by the storms of persecution and staggered by the winds of police brutality. You have been the veterans of creative suffering. Continue to work with the faith that unearned suffering is redemptive. Go back to Mississippi, go back to Alabama, go back to South Carolina, go back to Georgia, go back to Louisiana, go back to the slums and ghettos of our northern cities, knowing that somehow this situation can and will be changed. Let us not wallow in the valley of despair.

Which lines in this paragraph can be used as examples of metaphor? Select 3 options.

great trials and tribulations
storms of persecution
winds of police brutality
go back to Georgia
this situation can and will be changed
let us not wallow in the valley of despair

LLM: Read the excerpt from Dr. Martin Luther King Jr.’s "I Have a Dream" speech.

I am not unmindful that some of you have come here out of great trials and tribulations. Some of you have come fresh from narrow jail cells. Some of you have come from areas where your quest for freedom left you battered by the storms of persecution and staggered by the winds of police brutality. You have been the veterans of creative suffering. Continue to work with the faith that unearned suffering is redemptive. Go back to Mississippi, go back to Alabama, go back to South Carolina, go back to Georgia, go back to Louisiana, go back to the slums and ghettos of our northern cities, knowing that somehow this situation can and will be changed. Let us not wallow in the valley of despair.

Which lines in this paragraph can be used as examples of metaphor? Select 3 options.
A. great trials and tribulations
B. storms of persecution
C. winds of police brutality
D. go back to Georgia
E. this situation can and will be changed
F. let us not wallow in the valley of despair

Lessons Learned

When adding new tokens to the model, LoRA will be much worse. Use full fine-tuning to get better results.
Be very careful about chat templates. Every character/new line/space matters and not following that can make the model have worse performance.
For Qwen base models, leave the <|endoftext|> as the EOS token. Then you can train it to use other tokens like <|im_end|>. If you set the EOS token to <|im_end|>, the model will get confused.
For Qwen models in general, always put the <|endoftext|> at the end of each training example.