Instructions to use electroglyph/gemma-3-4b-it-unslop-GRPO-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use electroglyph/gemma-3-4b-it-unslop-GRPO-v3 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-GRPO-v3")
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-GRPO-v3")
model = AutoModelForImageTextToText.from_pretrained("electroglyph/gemma-3-4b-it-unslop-GRPO-v3")
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-GRPO-v3 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-GRPO-v3",
	filename="GGUF/gemma-3-4b-it-unslop-GRPO-v3-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 Settings

llama.cpp

How to use electroglyph/gemma-3-4b-it-unslop-GRPO-v3 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-GRPO-v3:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf electroglyph/gemma-3-4b-it-unslop-GRPO-v3: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-GRPO-v3:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf electroglyph/gemma-3-4b-it-unslop-GRPO-v3: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-GRPO-v3:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf electroglyph/gemma-3-4b-it-unslop-GRPO-v3: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-GRPO-v3:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf electroglyph/gemma-3-4b-it-unslop-GRPO-v3:UD-Q4_K_XL

Use Docker

docker model run hf.co/electroglyph/gemma-3-4b-it-unslop-GRPO-v3:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use electroglyph/gemma-3-4b-it-unslop-GRPO-v3 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-GRPO-v3"
# 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-GRPO-v3",
		"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-GRPO-v3:UD-Q4_K_XL

SGLang

How to use electroglyph/gemma-3-4b-it-unslop-GRPO-v3 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-GRPO-v3" \
    --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-GRPO-v3",
		"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-GRPO-v3" \
        --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-GRPO-v3",
		"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-GRPO-v3 with Ollama:
```
ollama run hf.co/electroglyph/gemma-3-4b-it-unslop-GRPO-v3:UD-Q4_K_XL
```

Unsloth Studio

How to use electroglyph/gemma-3-4b-it-unslop-GRPO-v3 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-GRPO-v3 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-GRPO-v3 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-GRPO-v3 to start chatting

Docker Model Runner
How to use electroglyph/gemma-3-4b-it-unslop-GRPO-v3 with Docker Model Runner:
```
docker model run hf.co/electroglyph/gemma-3-4b-it-unslop-GRPO-v3:UD-Q4_K_XL
```

Lemonade

How to use electroglyph/gemma-3-4b-it-unslop-GRPO-v3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull electroglyph/gemma-3-4b-it-unslop-GRPO-v3:UD-Q4_K_XL

Run and chat with the model

lemonade run user.gemma-3-4b-it-unslop-GRPO-v3-UD-Q4_K_XL

List all available models

lemonade list

Gemma 3 4b unslop experiment v3

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

Next version is here: gemma-3-4b-it-unslop-GSPO

Changes from my previous test

Temperature during training was at 1.0 this time around, model is a lot less weird
Rewards changed a little bit. I allowed a small number of sentences with 4+ commas instead of penalizing them all. This has cut down on the number of paranthetical phrases without completely eliminating them.
Lexical diversity score is a bit fancier this time. First I calculated MTLD for 600+ books I have and looked at the mean score. It was almost exactly 100.0, so that's the baseline I aimed for. MTLD of 80-120 all received full points (to avoid too much GRPO chaos), but deviations further than that get increasingly penalized.
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: 25

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for electroglyph/gemma-3-4b-it-unslop-GRPO-v3

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Quantized

(464)

this model