Instructions to use mshojaei77/gemma-3-4b-persian-v0-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mshojaei77/gemma-3-4b-persian-v0-abliterated with Transformers:

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

pipe = pipeline("image-text-to-text", model="mshojaei77/gemma-3-4b-persian-v0-abliterated")
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("mshojaei77/gemma-3-4b-persian-v0-abliterated")
model = AutoModelForMultimodalLM.from_pretrained("mshojaei77/gemma-3-4b-persian-v0-abliterated", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mshojaei77/gemma-3-4b-persian-v0-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mshojaei77/gemma-3-4b-persian-v0-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mshojaei77/gemma-3-4b-persian-v0-abliterated",
		"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/mshojaei77/gemma-3-4b-persian-v0-abliterated

SGLang

How to use mshojaei77/gemma-3-4b-persian-v0-abliterated 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 "mshojaei77/gemma-3-4b-persian-v0-abliterated" \
    --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": "mshojaei77/gemma-3-4b-persian-v0-abliterated",
		"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 "mshojaei77/gemma-3-4b-persian-v0-abliterated" \
        --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": "mshojaei77/gemma-3-4b-persian-v0-abliterated",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use mshojaei77/gemma-3-4b-persian-v0-abliterated with Docker Model Runner:
```
docker model run hf.co/mshojaei77/gemma-3-4b-persian-v0-abliterated
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:


models:
  - model: mlabonne/gemma-3-4b-it-abliterated
  - model: mshojaei77/gemma-3-4b-persian-v0
base_model: mlabonne/gemma-3-4b-it-abliterated
merge_method: slerp
dtype: bfloat16  # Better stability for precision-sensitive merges
parameters:
  density: 0.5
  weight: 
    - filter: "self_attn"
      value: [0.75, 0.4, 0.25, 0.4, 0.75]  # U-shaped attention weighting
    - filter: "mlp"
      value: [0.25, 0.6, 0.9, 0.6, 0.25]  # Λ-shaped MLP weighting
  t: [0.15, 0.35, 0.65, 0.35, 0.15]  # Optimized linguistic injection

generation_config = {
    "temperature": 1.1,
    "top_k": 50,
    "top_p": 0.9,
    "repetition_penalty": 1.15,
    "do_sample": True
}

Downloads last month: 14

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for mshojaei77/gemma-3-4b-persian-v0-abliterated

mlabonne/gemma-3-4b-it-abliterated

mshojaei77/gemma-3-4b-persian-v0

Merge model

this model

Quantizations

3 models