Instructions to use Capitaller/gemma_4E2B-it_finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Capitaller/gemma_4E2B-it_finetune with Transformers:

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

pipe = pipeline("image-text-to-text", model="Capitaller/gemma_4E2B-it_finetune")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Capitaller/gemma_4E2B-it_finetune")
model = AutoModelForImageTextToText.from_pretrained("Capitaller/gemma_4E2B-it_finetune")

llama-cpp-python

How to use Capitaller/gemma_4E2B-it_finetune with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Capitaller/gemma_4E2B-it_finetune",
	filename="gemma-4-e2b-it.F16-mmproj.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Capitaller/gemma_4E2B-it_finetune with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Capitaller/gemma_4E2B-it_finetune:F16
# Run inference directly in the terminal:
llama-cli -hf Capitaller/gemma_4E2B-it_finetune:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Capitaller/gemma_4E2B-it_finetune:F16
# Run inference directly in the terminal:
llama-cli -hf Capitaller/gemma_4E2B-it_finetune:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Capitaller/gemma_4E2B-it_finetune:F16
# Run inference directly in the terminal:
./llama-cli -hf Capitaller/gemma_4E2B-it_finetune:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Capitaller/gemma_4E2B-it_finetune:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Capitaller/gemma_4E2B-it_finetune:F16

Use Docker

docker model run hf.co/Capitaller/gemma_4E2B-it_finetune:F16

LM Studio
Jan

vLLM

How to use Capitaller/gemma_4E2B-it_finetune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Capitaller/gemma_4E2B-it_finetune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Capitaller/gemma_4E2B-it_finetune",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Capitaller/gemma_4E2B-it_finetune:F16

SGLang

How to use Capitaller/gemma_4E2B-it_finetune 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 "Capitaller/gemma_4E2B-it_finetune" \
    --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": "Capitaller/gemma_4E2B-it_finetune",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "Capitaller/gemma_4E2B-it_finetune" \
        --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": "Capitaller/gemma_4E2B-it_finetune",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use Capitaller/gemma_4E2B-it_finetune with Ollama:
```
ollama run hf.co/Capitaller/gemma_4E2B-it_finetune:F16
```

Unsloth Studio new

How to use Capitaller/gemma_4E2B-it_finetune 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 Capitaller/gemma_4E2B-it_finetune 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 Capitaller/gemma_4E2B-it_finetune to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Capitaller/gemma_4E2B-it_finetune to start chatting

Pi new

How to use Capitaller/gemma_4E2B-it_finetune with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Capitaller/gemma_4E2B-it_finetune:F16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Capitaller/gemma_4E2B-it_finetune:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Capitaller/gemma_4E2B-it_finetune with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Capitaller/gemma_4E2B-it_finetune:F16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Capitaller/gemma_4E2B-it_finetune:F16

Run Hermes

hermes

Docker Model Runner
How to use Capitaller/gemma_4E2B-it_finetune with Docker Model Runner:
```
docker model run hf.co/Capitaller/gemma_4E2B-it_finetune:F16
```

Lemonade

How to use Capitaller/gemma_4E2B-it_finetune with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Capitaller/gemma_4E2B-it_finetune:F16

Run and chat with the model

lemonade run user.gemma_4E2B-it_finetune-F16

List all available models

lemonade list

Gemma-4-E2B-it Agentic AI on AWS (Instruct)

This model is an instruction-tuned (Supervised Fine-Tuning) version of Google's Gemma-4-E2B-it. It has been specialized to act as a conversational assistant, answering complex architectural questions regarding Agentic AI systems, frameworks, and protocols on Amazon Web Services (AWS).

The model was fine-tuned using Unsloth to enhance its ability to reason about AWS architectures and provide actionable, structured guidance based on official AWS prescriptive documentation.

Model Details

Base Model: google/gemma-4-e2b-it (via unsloth/gemma-4-E2B-it)
Training Type: Supervised Fine-Tuning (Instruction/Chat)
Domain focus: AWS Architecture, Agentic AI, Frameworks, and Protocols (MCP, etc.)
Language: English
Library: Unsloth / Hugging Face Transformers

Dataset

The model was trained on instruction-response pairs sourced from AWS Prescriptive Guidance: Agentic AI frameworks, platforms, protocols, and tools on AWS. It has been taught to answer queries concisely and provide highly technical, context-aware AWS architecture advice based on modern Agentic standards.

Training Configuration

Unlike a base model, this model already understands conversational flow. Fine-tuning was constrained to the attention and MLP layers to smoothly adapt its persona and specific technical knowledge without causing catastrophic forgetting.

Method: PEFT / LoRA
LoRA Rank (r): 16 (Standard for Instruct tuning)
LoRA Alpha: 16 (or 32, scaled for optimal learning)
Target Modules: Attention and MLP modules (q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj)
Precision: 4-bit quantization (QLoRA) during training
Optimizer: Paged AdamW 8-bit

How to Use

Because this is an Instruct model, you must use the standard Gemma chat template when querying it. You can interact with it exactly like a standard chatbot.

You can load it using Transformers or Unsloth:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Capitaller/gemma_4E2B-it_finetune"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Ensure you use the proper chat format
messages = [
    {"role": "user", "content": "How should I design an Agentic AI architecture on AWS that uses the Model Context Protocol (MCP)?"},
]

inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_tensors="pt"
)

outputs = model.generate(inputs, max_new_tokens=256, temperature=0.7)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Prompting Tips

This model is designed to be highly instructional and responsive to direct questions.

Ask clear, technical questions: "What are the recommended AWS compute platforms for hosting an MCP server?"
Request specific structures: "Write a brief step-by-step guide on securing an AI agent communication channel on AWS."

Downloads last month: 64

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

8-bit