Instructions to use jetbabareal/gemma-3-1b-elite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jetbabareal/gemma-3-1b-elite with Transformers:

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

pipe = pipeline("text-generation", model="jetbabareal/gemma-3-1b-elite")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jetbabareal/gemma-3-1b-elite")
model = AutoModelForCausalLM.from_pretrained("jetbabareal/gemma-3-1b-elite", 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 jetbabareal/gemma-3-1b-elite with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jetbabareal/gemma-3-1b-elite"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jetbabareal/gemma-3-1b-elite",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jetbabareal/gemma-3-1b-elite

SGLang

How to use jetbabareal/gemma-3-1b-elite 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 "jetbabareal/gemma-3-1b-elite" \
    --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": "jetbabareal/gemma-3-1b-elite",
		"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 "jetbabareal/gemma-3-1b-elite" \
        --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": "jetbabareal/gemma-3-1b-elite",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jetbabareal/gemma-3-1b-elite with Docker Model Runner:
```
docker model run hf.co/jetbabareal/gemma-3-1b-elite
```

Gemma 3 - 1B Elite Fusion (Experimental)

This model is the result of a specialized "Elite Neuron Fusion" technique applied to the Gemma architecture. It is not a standard model merge; rather, it uses a surgical approach to inject reasoning capabilities from earlier layers into deeper layers.

🔬 Methodology: Elite Neuron Fusion

Unlike traditional merging methods (SLERP, Linear) that blend entire weights, this method uses a density-based injection algorithm.

Layer Analysis: We identified specific resonance pairs between source (early-mid) and target (mid-deep) layers.
Top-k Filtering: For each pair, we calculated the delta vector (difference).
Density Selection: Only the top 20% of neurons with the highest activation/change were selected.
Injection: These "elite" neurons were injected into the target layers with a specific alpha scaling factor.

Technical Configuration

Source Layers: 16, 15, 14, 13, 12
Target Layers: 17, 18, 19, 20, 21
Density: 0.20 (Only 20% of weights are modified per layer)
Alpha: 0.40
Logic: Target = Target + (Delta * Mask * Alpha)

🎯 Goal

The primary goal of this experiment is to enhance the reasoning and logic capabilities of smaller language models (1B-2B range) without destroying their pre-trained knowledge base or causing severe hallucinations.

💻 Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "jetbabareal/gemma-3-1b-elite"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

input_text = "Question: ?\nAnswer:"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=50)
print(tokenizer.decode(outputs[0]))

Developer: jetbabareal Algorithm: Elite Neuron Fusion

Downloads last month: 22

Safetensors

Model size

1.0B params

Tensor type

F16

Model tree for jetbabareal/gemma-3-1b-elite

Base model

google/gemma-3-1b-pt

Finetuned

google/gemma-3-1b-it

Finetuned

(556)

this model

Finetunes

1 model