Instructions to use Roman0/functiongemma-270m-it-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Roman0/functiongemma-270m-it-heretic with Transformers:

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

pipe = pipeline("text-generation", model="Roman0/functiongemma-270m-it-heretic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Roman0/functiongemma-270m-it-heretic")
model = AutoModelForCausalLM.from_pretrained("Roman0/functiongemma-270m-it-heretic", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Roman0/functiongemma-270m-it-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Roman0/functiongemma-270m-it-heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Roman0/functiongemma-270m-it-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Roman0/functiongemma-270m-it-heretic

SGLang

How to use Roman0/functiongemma-270m-it-heretic 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 "Roman0/functiongemma-270m-it-heretic" \
    --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": "Roman0/functiongemma-270m-it-heretic",
		"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 "Roman0/functiongemma-270m-it-heretic" \
        --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": "Roman0/functiongemma-270m-it-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Roman0/functiongemma-270m-it-heretic with Docker Model Runner:
```
docker model run hf.co/Roman0/functiongemma-270m-it-heretic
```

Roman0 commited on Dec 19, 2025

Commit

3fea153

1 Parent(s): aff4b27

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +10 -10

README.md CHANGED Viewed

@@ -24,21 +24,21 @@ extra_gated_button_content: Acknowledge license
 | Parameter | Value |
 | :-------- | :---: |
 | **direction_index** | per layer |
-| **attn.o_proj.max_weight** | 1.25 |
-| **attn.o_proj.max_weight_position** | 14.09 |
-| **attn.o_proj.min_weight** | 0.92 |
-| **attn.o_proj.min_weight_distance** | 6.34 |
-| **mlp.down_proj.max_weight** | 1.49 |
-| **mlp.down_proj.max_weight_position** | 11.73 |
-| **mlp.down_proj.min_weight** | 0.42 |
-| **mlp.down_proj.min_weight_distance** | 5.54 |
 ## Performance
 | Metric | This model | Original model ([google/functiongemma-270m-it](https://huggingface.co/google/functiongemma-270m-it)) |
 | :----- | :--------: | :---------------------------: |
-| **KL divergence** | 0.2851 | 0 *(by definition)* |
-| **Refusals** | 5/100 | 100/100 |
 -----

 | Parameter | Value |
 | :-------- | :---: |
 | **direction_index** | per layer |
+| **attn.o_proj.max_weight** | 1.33 |
+| **attn.o_proj.max_weight_position** | 12.65 |
+| **attn.o_proj.min_weight** | 0.85 |
+| **attn.o_proj.min_weight_distance** | 4.36 |
+| **mlp.down_proj.max_weight** | 1.46 |
+| **mlp.down_proj.max_weight_position** | 12.22 |
+| **mlp.down_proj.min_weight** | 1.40 |
+| **mlp.down_proj.min_weight_distance** | 4.97 |
 ## Performance
 | Metric | This model | Original model ([google/functiongemma-270m-it](https://huggingface.co/google/functiongemma-270m-it)) |
 | :----- | :--------: | :---------------------------: |
+| **KL divergence** | 0.2617 | 0 *(by definition)* |
+| **Refusals** | 2/100 | 100/100 |
 -----