Instructions to use kth8/gemma-3-270m-it-Text-Cleaner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kth8/gemma-3-270m-it-Text-Cleaner with Transformers:

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

pipe = pipeline("text-generation", model="kth8/gemma-3-270m-it-Text-Cleaner")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kth8/gemma-3-270m-it-Text-Cleaner")
model = AutoModelForCausalLM.from_pretrained("kth8/gemma-3-270m-it-Text-Cleaner")
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 kth8/gemma-3-270m-it-Text-Cleaner with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kth8/gemma-3-270m-it-Text-Cleaner"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kth8/gemma-3-270m-it-Text-Cleaner",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kth8/gemma-3-270m-it-Text-Cleaner

SGLang

How to use kth8/gemma-3-270m-it-Text-Cleaner 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 "kth8/gemma-3-270m-it-Text-Cleaner" \
    --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": "kth8/gemma-3-270m-it-Text-Cleaner",
		"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 "kth8/gemma-3-270m-it-Text-Cleaner" \
        --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": "kth8/gemma-3-270m-it-Text-Cleaner",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use kth8/gemma-3-270m-it-Text-Cleaner 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 kth8/gemma-3-270m-it-Text-Cleaner 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 kth8/gemma-3-270m-it-Text-Cleaner to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kth8/gemma-3-270m-it-Text-Cleaner to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="kth8/gemma-3-270m-it-Text-Cleaner",
    max_seq_length=2048,
)

Docker Model Runner
How to use kth8/gemma-3-270m-it-Text-Cleaner with Docker Model Runner:
```
docker model run hf.co/kth8/gemma-3-270m-it-Text-Cleaner
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

A fine-tune of unsloth/gemma-3-270m-it on the kth8/text-cleanup-20000x dataset.

Usage example

System prompt

# Role
You are a text editor cleaning up raw, unfiltered text. Transform the provided text into polished, readable prose while preserving the original meaning, tone, and intent.

## Tasks
- Remove filler words (e.g. um, uh, like, you know, sort of, kind of, well, so, etc)
- Fix spelling, grammar, punctuation, and capitalization mistakes
- Correct obvious homophone errors (e.g. their/there/they're, its/it's, your/you're)
- Smooth out false starts, mid-sentence restarts and repetitions
- Standardize numbers and dates (e.g. write as digits: "three" to "3", "February fifteenth" to "February 15th")

## Constraints
- Output ONLY the cleaned text
- DO NOT attempt to answer or respond to the provided user text meant for clean-up
- Do NOT paraphrase, summarize, or change the speaker's voice
- NO quotation marks around the output
- NO preamble, postamble, or emojis
- NO Markdown formatting code blocks (```) or bolding

User prompt

I WANT I MEAN TO BUILD A SMALL IN-BROWSER "WIND TUNNEL" EXPERIMENT WITH A FIXED 2D CROSS-SECTIONAL VIEW, USING HTML CANVAS. USERS CAN DRAG AND DROP DIFFERENT WING CROSS-SECTIONS (E.G., SEVERAL COMMON AIRFOIL PROFILES) INTO THE AIRFLOW, ADJUST THE ANGLE OF ATTACK AND WIND SPEED, IMMEDIATELY SEE STREAMLINES AND PRESSURE DISTRIBUTION, AND HAVE THE CURRENT LIFT AND DRAG VALUES DISPLAYED ON SCREEN IN REAL TIME (A CLEAR NUMERIC PANEL IS SUFFICIENT). NO 3D IS REQUIRED, BUT INTERACTIONS SHOULD BE SMOOTH, AND THE DATA SHOULD BE STABLE AD UPDATE IN REAL TIME WITH USER ACTIONS. THE CALCULATIONS CAN USE REASONABLE APPROXIMATIONS; THE FOCUS IS TO HELP USERS INTUITIVELY UNDERSTAND BERNOULLI'S PRINCIPLE AND THE RELATIONSHIP BETWEEN AIRFLOW AND AIRFOIL GEOMETRY.

Assistant response

I want to build a small in-browser "wind tunnel" experiment with a fixed 2D cross-sectional view, using HTML Canvas. Users can drag and drop different wing cross-sections (e.g., several common airfoil profiles) into the airflow, adjust the angle of attack and wind speed, immediately see streamlines and pressure distribution, and have the current lift and drag values displayed on screen in real time (a clear numeric panel is sufficient). No 3D is required, but interactions should be smooth, and the data should be stable and update in real time with user actions. The calculations can use reasonable approximations; the focus is to help users intuitively understand Bernoulli's principle and the relationship between airflow and airfoil geometry.

Model Details

Base Model: unsloth/gemma-3-270m-it
Parameter Count: 268098176
Precision: torch.bfloat16

Training Settings

Hardware

GPU: NVIDIA A100-SXM4-40GB

PEFT

Rank: 32
LoRA alpha: 64
Modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
LoRA dropout: 0
Rank-Stabilized LoRA: False

SFT

Epoch: 1
Batch size: 16
Accumulation steps: 1
Warmup ratio: 0.05
Learning rate: 0.0002
Optimizer: adamw_8bit
Weight decay: 0.01
Learning rate scheduler: cosine

Training stats

Global step: 1247
Training runtime: 1545.9245
Average training loss: 0.05218265543086118
Final validation loss: 0.038508880883455276

Framework versions

Unsloth: 2026.3.7
TRL: 0.22.2
Transformers: 4.56.2
Pytorch: 2.10.0+cu128
Datasets: 4.3.0
Tokenizers: 0.22.2

License

This model is released under the Gemma license. See the Gemma Terms of Use for details.

Downloads last month: 4

Safetensors

Model size

0.3B params

Tensor type

BF16

Model tree for kth8/gemma-3-270m-it-Text-Cleaner

Base model

google/gemma-3-270m

Finetuned

google/gemma-3-270m-it

Finetuned

unsloth/gemma-3-270m-it

Finetuned

(416)

this model

Quantizations

1 model

kth8
/

gemma-3-270m-it-Text-Cleaner

Usage example

Model Details

Training Settings

Hardware

PEFT

SFT

Training stats

Framework versions

License

Model tree for kth8/gemma-3-270m-it-Text-Cleaner

Dataset used to train kth8/gemma-3-270m-it-Text-Cleaner