Instructions to use Folx/qwen3-0.6b-pl-text-normalization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Folx/qwen3-0.6b-pl-text-normalization with Transformers:

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

pipe = pipeline("text-generation", model="Folx/qwen3-0.6b-pl-text-normalization")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Folx/qwen3-0.6b-pl-text-normalization")
model = AutoModelForCausalLM.from_pretrained("Folx/qwen3-0.6b-pl-text-normalization")
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 Folx/qwen3-0.6b-pl-text-normalization with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Folx/qwen3-0.6b-pl-text-normalization"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Folx/qwen3-0.6b-pl-text-normalization",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Folx/qwen3-0.6b-pl-text-normalization

SGLang

How to use Folx/qwen3-0.6b-pl-text-normalization 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 "Folx/qwen3-0.6b-pl-text-normalization" \
    --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": "Folx/qwen3-0.6b-pl-text-normalization",
		"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 "Folx/qwen3-0.6b-pl-text-normalization" \
        --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": "Folx/qwen3-0.6b-pl-text-normalization",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Folx/qwen3-0.6b-pl-text-normalization with Docker Model Runner:
```
docker model run hf.co/Folx/qwen3-0.6b-pl-text-normalization
```

Fine-tuning to achieve specific results

by dely - opened 26 days ago

Discussion

dely

26 days ago

I would like to fine-tune this model using my own examples, as I have noticed that it does not perform particularly well when it comes to statistical analyses, for example:

Input: "Do powiatów o najwyższej stopie bezrobocia należały: szydłowiecki – 22,5% (wzrost o 0,2 punktu procentowego w skali roku)"

Model output: "Do powiatów o najwyższej stopie bezrobocia należały: szydłowiecki – dwadzieścia dwa i pół procenta (wzrost o zero dwie dziesiąte punktu procentowego w skali roku)"

I would like the output to look like this:

"Do powiatów o najwyższej stopie bezrobocia należały: szydłowiecki – dwadzieścia dwa i pół procenta (wzrost o dwie dziesiąte punktu procentowego w skali roku)"

I have a large number of correctly constructed sentences – examples generated using Gemini Flash 3.5. What should the training set look like? Should it consist of full sentences with problematic cases, or just numbers, e.g.

{‘messages’: [{‘role’: ‘system’, ‘content’: ‘Zamień tekst pisany na formę mówioną (normalizacja tekstu dla TTS).’}, {‘role’: “user”, ‘content’: ‘Do powiatów o najwyższej stopie bezrobocia należały: szydłowiecki – 22,5% (wzrost o 0,2 punktu procentowego w skali roku)’}, {‘role’: “assistant”, ‘content’: ‘Do powiatów o najwyższej stopie bezrobocia należały: szydłowiecki – dwadzieścia dwa i pięć dziesiątych procent (spadek o dwie dziesiąte punktu procentowego w skali roku)’}]}

{‘messages’: [{‘role’: ‘system’, ‘content’: ‘Zamień tekst pisany na formę mówioną (normalizacja tekstu dla TTS).’}, {‘role’: “user”, ‘content’: ‘0,2 punktu procentowego’}, {‘role’: “assistant”, ‘content’: ‘dwie dziesiąte punktu procentowego’}]}

Thank you.

krzynio

Folx.it org 26 days ago

Hi. Training set should consist of full sentences or a mix of both.

dely

26 days ago

Thank you.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment