Instructions to use electroglyph/gemma-3-4b-it-unslop-GSPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use electroglyph/gemma-3-4b-it-unslop-GSPO with Transformers:

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

pipe = pipeline("image-text-to-text", model="electroglyph/gemma-3-4b-it-unslop-GSPO")
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("electroglyph/gemma-3-4b-it-unslop-GSPO")
model = AutoModelForImageTextToText.from_pretrained("electroglyph/gemma-3-4b-it-unslop-GSPO")
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 electroglyph/gemma-3-4b-it-unslop-GSPO with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="electroglyph/gemma-3-4b-it-unslop-GSPO",
	filename="GGUF/gemma-3-4b-it-unslop-GSPO-UD-Q4_K_XL.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 electroglyph/gemma-3-4b-it-unslop-GSPO with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf electroglyph/gemma-3-4b-it-unslop-GSPO:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf electroglyph/gemma-3-4b-it-unslop-GSPO:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf electroglyph/gemma-3-4b-it-unslop-GSPO:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf electroglyph/gemma-3-4b-it-unslop-GSPO:UD-Q4_K_XL

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 electroglyph/gemma-3-4b-it-unslop-GSPO:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf electroglyph/gemma-3-4b-it-unslop-GSPO:UD-Q4_K_XL

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 electroglyph/gemma-3-4b-it-unslop-GSPO:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf electroglyph/gemma-3-4b-it-unslop-GSPO:UD-Q4_K_XL

Use Docker

docker model run hf.co/electroglyph/gemma-3-4b-it-unslop-GSPO:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use electroglyph/gemma-3-4b-it-unslop-GSPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "electroglyph/gemma-3-4b-it-unslop-GSPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "electroglyph/gemma-3-4b-it-unslop-GSPO",
		"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/electroglyph/gemma-3-4b-it-unslop-GSPO:UD-Q4_K_XL

SGLang

How to use electroglyph/gemma-3-4b-it-unslop-GSPO 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 "electroglyph/gemma-3-4b-it-unslop-GSPO" \
    --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": "electroglyph/gemma-3-4b-it-unslop-GSPO",
		"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 "electroglyph/gemma-3-4b-it-unslop-GSPO" \
        --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": "electroglyph/gemma-3-4b-it-unslop-GSPO",
		"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 electroglyph/gemma-3-4b-it-unslop-GSPO with Ollama:
```
ollama run hf.co/electroglyph/gemma-3-4b-it-unslop-GSPO:UD-Q4_K_XL
```

Unsloth Studio new

How to use electroglyph/gemma-3-4b-it-unslop-GSPO 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 electroglyph/gemma-3-4b-it-unslop-GSPO 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 electroglyph/gemma-3-4b-it-unslop-GSPO to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for electroglyph/gemma-3-4b-it-unslop-GSPO to start chatting

Docker Model Runner
How to use electroglyph/gemma-3-4b-it-unslop-GSPO with Docker Model Runner:
```
docker model run hf.co/electroglyph/gemma-3-4b-it-unslop-GSPO:UD-Q4_K_XL
```

Lemonade

How to use electroglyph/gemma-3-4b-it-unslop-GSPO with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull electroglyph/gemma-3-4b-it-unslop-GSPO:UD-Q4_K_XL

Run and chat with the model

lemonade run user.gemma-3-4b-it-unslop-GSPO-UD-Q4_K_XL

List all available models

lemonade list

Gemma 3 4b unslop experiment v4

An unslop finetune of google/gemma-3-4b-it

Changes from my previous test

Trying GSPO for the first time. I've settled on a much lower rank (16) than the 64 in my last finetune. It was really hard to get lower ranks stable with my weird reward function during GRPO. The extra stability from GSPO seems to have opened up some extra options though.
This finetune feels quite a bit different. Markdown wasn't suppressed as successfully as last time, but the lower rank gave it much different feel, too.
I think I prefer my previous finetune but I'm not 100% sure yet.
I've uploaded a UD-Q4_K_XL GGUF with settings that I grabbed from Unsloth's quant using my lil utility: quant_clone

Training technique:

Basically the same as last time plus the minor changes above.

training code: train.py

Downloads last month: 24

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for electroglyph/gemma-3-4b-it-unslop-GSPO

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Quantized

(221)

this model