Instructions to use piotrleniartek/eyegemma-1.5-4b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use piotrleniartek/eyegemma-1.5-4b-it with Transformers:

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

pipe = pipeline("image-text-to-text", model="piotrleniartek/eyegemma-1.5-4b-it")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("piotrleniartek/eyegemma-1.5-4b-it")
model = AutoModelForMultimodalLM.from_pretrained("piotrleniartek/eyegemma-1.5-4b-it")
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?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use piotrleniartek/eyegemma-1.5-4b-it with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="piotrleniartek/eyegemma-1.5-4b-it",
	filename="eyegemma-1.5-4b-it.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 Settings

llama.cpp

How to use piotrleniartek/eyegemma-1.5-4b-it with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf piotrleniartek/eyegemma-1.5-4b-it
# Run inference directly in the terminal:
llama-cli -hf piotrleniartek/eyegemma-1.5-4b-it

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf piotrleniartek/eyegemma-1.5-4b-it
# Run inference directly in the terminal:
llama-cli -hf piotrleniartek/eyegemma-1.5-4b-it

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 piotrleniartek/eyegemma-1.5-4b-it
# Run inference directly in the terminal:
./llama-cli -hf piotrleniartek/eyegemma-1.5-4b-it

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 piotrleniartek/eyegemma-1.5-4b-it
# Run inference directly in the terminal:
./build/bin/llama-cli -hf piotrleniartek/eyegemma-1.5-4b-it

Use Docker

docker model run hf.co/piotrleniartek/eyegemma-1.5-4b-it

LM Studio
Jan

vLLM

How to use piotrleniartek/eyegemma-1.5-4b-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "piotrleniartek/eyegemma-1.5-4b-it"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "piotrleniartek/eyegemma-1.5-4b-it",
		"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/piotrleniartek/eyegemma-1.5-4b-it

SGLang

How to use piotrleniartek/eyegemma-1.5-4b-it 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 "piotrleniartek/eyegemma-1.5-4b-it" \
    --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": "piotrleniartek/eyegemma-1.5-4b-it",
		"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 "piotrleniartek/eyegemma-1.5-4b-it" \
        --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": "piotrleniartek/eyegemma-1.5-4b-it",
		"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 piotrleniartek/eyegemma-1.5-4b-it with Ollama:
```
ollama run hf.co/piotrleniartek/eyegemma-1.5-4b-it
```

Unsloth Studio

How to use piotrleniartek/eyegemma-1.5-4b-it 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 piotrleniartek/eyegemma-1.5-4b-it 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 piotrleniartek/eyegemma-1.5-4b-it to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for piotrleniartek/eyegemma-1.5-4b-it to start chatting

Atomic Chat new
Docker Model Runner
How to use piotrleniartek/eyegemma-1.5-4b-it with Docker Model Runner:
```
docker model run hf.co/piotrleniartek/eyegemma-1.5-4b-it
```

Lemonade

How to use piotrleniartek/eyegemma-1.5-4b-it with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull piotrleniartek/eyegemma-1.5-4b-it

Run and chat with the model

lemonade run user.eyegemma-1.5-4b-it-{{QUANT_TAG}}

List all available models

lemonade list

Model Card for eyegemma-1.5-4b-it

This model is a fine-tuned version of google/medgemma-1.5-4b-it. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="piotrleniartek/eyegemma-1.5-4b-it", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Framework versions

TRL: 0.28.0
Transformers: 5.2.0
Pytorch: 2.10.0+cu128
Datasets: 4.5.0
Tokenizers: 0.22.2

Citations

Cite TRL as:

@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}

Downloads last month: 7

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for piotrleniartek/eyegemma-1.5-4b-it

Base model

google/medgemma-1.5-4b-it

Quantized

(34)

this model