Instructions to use electroglyph/gemma-3-4b-it-unslop-GRPO 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 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")
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 AutoModel
model = AutoModel.from_pretrained("electroglyph/gemma-3-4b-it-unslop-GRPO", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use electroglyph/gemma-3-4b-it-unslop-GRPO with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf electroglyph/gemma-3-4b-it-unslop-GRPO:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf electroglyph/gemma-3-4b-it-unslop-GRPO:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf electroglyph/gemma-3-4b-it-unslop-GRPO:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf electroglyph/gemma-3-4b-it-unslop-GRPO:Q4_K_M

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:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf electroglyph/gemma-3-4b-it-unslop-GRPO:Q4_K_M

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:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf electroglyph/gemma-3-4b-it-unslop-GRPO:Q4_K_M

Use Docker

docker model run hf.co/electroglyph/gemma-3-4b-it-unslop-GRPO:Q4_K_M

LM Studio
Jan

vLLM

How to use electroglyph/gemma-3-4b-it-unslop-GRPO 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"
# 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",
		"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:Q4_K_M

SGLang

How to use electroglyph/gemma-3-4b-it-unslop-GRPO 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" \
    --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",
		"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" \
        --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",
		"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 with Ollama:
```
ollama run hf.co/electroglyph/gemma-3-4b-it-unslop-GRPO:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use electroglyph/gemma-3-4b-it-unslop-GRPO with Docker Model Runner:
```
docker model run hf.co/electroglyph/gemma-3-4b-it-unslop-GRPO:Q4_K_M
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull electroglyph/gemma-3-4b-it-unslop-GRPO:Q4_K_M

Run and chat with the model

lemonade run user.gemma-3-4b-it-unslop-GRPO-Q4_K_M

List all available models

lemonade list

Atomic Chat

Gemma 3 4b unslop experiment

Update

v2 of this model is here

Okay, I've received some good feedback.

This finetune is mostly geared towards fiction writing, unfortunately all the RP slop is still present.

Also, intelligence has been damaged a bit, as instruction following isn't great sometimes.

On the plus side, I'm pretty happy with it's new writing style when it does work.

Changes for the next version:

I'll diversify my dataset a little to hopefully mitigate some overfitting on the prompt format
I'll experiment with parameters like learning rate and LoRA rank a bit more
I'll see about including some RP data in my statistical analysis so I can target some of that slop, too

This is my first finetune. I used GRPO to reduce slop output.

This is a LoRA adapter, it needs to be merged with google/gemma-3-4b-it

I'll also upload a Q4_K_M GGUF made with unsloth's imatrix.

Tuning technique:

I generated lots of sample text and then sorted all bigrams and trigrams by frequency.

I added some of these to the reward function and penalized their use.

I also added some regex filters for comma overuse, and some sloppy phrasing, etc.

If the prompt doesn't include "rain", but model output includes rain, it gets penalized.

Same thing for "air". Gemma 3 LOVES to talk about rain and how the air tastes (or clings, etc.)... no more.

200 steps into training I activate lexical diversity comparison. It penalizes MTLD < 100, gives increasing rewards up to 120.

There's a callback for early stopping if reward stays high, but it didn't kick in this run.

This was trained on ~15 million tokens on a single 3090. I'm sharing my code so people can try their own finetuning runs.

I'll probably keep iterating on this a bit, and may update this model.

training code: train.py

I can't share my dataset, but here's an example of what it looks like: dataset_example.json

Gemma 3 4b common bigrams, most common first: bigrams.txt

Gemma 3 4b common trigrams, most common first: trigrams.txt

Downloads last month: 11

GGUF

Model size

4B params

Architecture

gemma3

Hardware compatibility

4-bit

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

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Quantized

(487)

this model