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

Libraries

How to use kth8/gemma-3-270m-it-JSON-Fixer with Transformers:

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

pipe = pipeline("text-generation", model="kth8/gemma-3-270m-it-JSON-Fixer")
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-JSON-Fixer")
model = AutoModelForCausalLM.from_pretrained("kth8/gemma-3-270m-it-JSON-Fixer")
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-JSON-Fixer 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-JSON-Fixer"
# 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-JSON-Fixer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kth8/gemma-3-270m-it-JSON-Fixer

SGLang

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

Unsloth Studio

How to use kth8/gemma-3-270m-it-JSON-Fixer 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-JSON-Fixer 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-JSON-Fixer 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-JSON-Fixer 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-JSON-Fixer",
    max_seq_length=2048,
)

Docker Model Runner
How to use kth8/gemma-3-270m-it-JSON-Fixer with Docker Model Runner:
```
docker model run hf.co/kth8/gemma-3-270m-it-JSON-Fixer
```
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/json-fix-25000x dataset.

Usage example

System prompt

You are a JSON formatting specialist. Convert the provided JSON data into valid JSON format with 2 line indent and no additional commentary.

User prompt

The JSON is:\n[{\"name\":\"John Doe\", \"jobTitle\":Software Engineer, \"department\": \"Research and Development\"],, {\"name\"\"Jane Smith\", \"jobTitle\":\"Data Analyst', \"department\":\"Marketing and Sales\"}, ]    //\" comment\n-- end --

Assistant response

[
  {
    "name": "John Doe",
    "jobTitle": "Software Engineer",
    "department": "Research and Development"
  },
  {
    "name": "Jane Smith",
    "jobTitle": "Data Analyst",
    "department": "Marketing and Sales"
  }
]

Model Details

Base Model: unsloth/gemma-3-270m-it
Parameter Count: 268,098,176
Precision: torch.bfloat16

Hardware

GPU: NVIDIA RTX PRO 6000 Blackwell Server Edition
Announced: Mar 17th, 2025
Release Date: Mar 18th, 2025
Memory Type: GDDR7
Bandwidth: 1.79 TB/s
Memory Size: 96 GB
Memory Bus: 512 bit
Shading Units: 24064
TDP: 600W
FP16 (half): 126.0 TFLOPS (1:1)

Training Settings

PEFT

Rank: 32
LoRA alpha: 64
Modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Gradient checkpointing: unsloth

SFT

Epoch: 2
Batch size: 32
Gradient Accumulation steps: 1
Warmup ratio: 0.05
Learning rate: 0.0004
Optimizer: adamw_torch_fused
Learning rate scheduler: cosine
Max seq length: 2048

Training stats

Date: 2026-03-23T04:39:38.019077
Peak VRAM usage: 64.5 GB
Global step: 1538
Training runtime (seconds): 1142.9274
Average training loss: 0.004019292104312295
Final validation loss: 0.0014343492221087217

Framework versions

Unsloth: 2026.3.10
TRL: 0.22.2
Transformers: 4.56.2
Pytorch: 2.10.0+cu128
Datasets: 4.8.3
Tokenizers: 0.22.2

License

This model is released under the Gemma license. See the Gemma Terms of Use and Prohibited Use Policy regarding the use of Gemma-generated content.

Downloads last month: 4

Safetensors

Model size

0.3B params

Tensor type

BF16

Model tree for kth8/gemma-3-270m-it-JSON-Fixer

Base model

google/gemma-3-270m

Finetuned

google/gemma-3-270m-it

Finetuned

unsloth/gemma-3-270m-it

Finetuned

(392)

this model

Quantizations

1 model

kth8
/

gemma-3-270m-it-JSON-Fixer

Usage example

Model Details

Hardware

Training Settings

PEFT

SFT

Training stats

Framework versions

License

Model tree for kth8/gemma-3-270m-it-JSON-Fixer

Dataset used to train kth8/gemma-3-270m-it-JSON-Fixer