Instructions to use empgces/gemma3-270m-grounded-behavior-finetuned-v9 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use empgces/gemma3-270m-grounded-behavior-finetuned-v9 with Transformers:

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

pipe = pipeline("text-generation", model="empgces/gemma3-270m-grounded-behavior-finetuned-v9")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("empgces/gemma3-270m-grounded-behavior-finetuned-v9")
model = AutoModelForCausalLM.from_pretrained("empgces/gemma3-270m-grounded-behavior-finetuned-v9", 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]:]))

PEFT
How to use empgces/gemma3-270m-grounded-behavior-finetuned-v9 with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use empgces/gemma3-270m-grounded-behavior-finetuned-v9 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "empgces/gemma3-270m-grounded-behavior-finetuned-v9"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "empgces/gemma3-270m-grounded-behavior-finetuned-v9",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/empgces/gemma3-270m-grounded-behavior-finetuned-v9

SGLang

How to use empgces/gemma3-270m-grounded-behavior-finetuned-v9 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 "empgces/gemma3-270m-grounded-behavior-finetuned-v9" \
    --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": "empgces/gemma3-270m-grounded-behavior-finetuned-v9",
		"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 "empgces/gemma3-270m-grounded-behavior-finetuned-v9" \
        --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": "empgces/gemma3-270m-grounded-behavior-finetuned-v9",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use empgces/gemma3-270m-grounded-behavior-finetuned-v9 with Docker Model Runner:
```
docker model run hf.co/empgces/gemma3-270m-grounded-behavior-finetuned-v9
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Gemma 3 270M Grounded Behavior — Fine-tuned V9

Modelo fine-tuned a partir de unsloth/gemma-3-270m-it com Unsloth e LoRA. Os pesos LoRA foram fundidos no modelo base e publicados em 16-bit.

Treino

Dataset: empgces/grounded-behavior-n1-pt
Épocas: 2
Exemplos de treino: 4440
Passos realizados: 1110
Learning rate: 0.0002
LoRA rank: 16
LoRA alpha: 32

Avaliação desta execução

Normalized Match: 86.00%
Prediction in Context: 98.00%
Loss final: 0.121574

GGUF

A versão GGUF está em empgces/gemma3-270m-grounded-behavior-finetuned-v9-GGUF.

Prompt

Utilize o chat template incluído no tokenizer. O treino pede respostas curtas, completas e estritamente fundamentadas no contexto fornecido.

Downloads last month: 9

Safetensors

Model size

0.3B params

Tensor type

BF16

Model tree for empgces/gemma3-270m-grounded-behavior-finetuned-v9

Base model

google/gemma-3-270m

Finetuned

google/gemma-3-270m-it

Finetuned

unsloth/gemma-3-270m-it

Finetuned

(423)

this model

Quantizations

1 model

empgces
/

gemma3-270m-grounded-behavior-finetuned-v9

Gemma 3 270M Grounded Behavior — Fine-tuned V9

Treino

Avaliação desta execução

GGUF

Prompt

Model tree for empgces/gemma3-270m-grounded-behavior-finetuned-v9

Dataset used to train empgces/gemma3-270m-grounded-behavior-finetuned-v9