Instructions to use alifzl/zhaav-gemma3-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alifzl/zhaav-gemma3-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="alifzl/zhaav-gemma3-4B")
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("alifzl/zhaav-gemma3-4B")
model = AutoModelForImageTextToText.from_pretrained("alifzl/zhaav-gemma3-4B")
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 alifzl/zhaav-gemma3-4B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="alifzl/zhaav-gemma3-4B",
	filename="zhaav-gemma3-4B.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"
					}
				}
			]
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use alifzl/zhaav-gemma3-4B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf alifzl/zhaav-gemma3-4B:Q8_0
# Run inference directly in the terminal:
llama-cli -hf alifzl/zhaav-gemma3-4B:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf alifzl/zhaav-gemma3-4B:Q8_0
# Run inference directly in the terminal:
llama-cli -hf alifzl/zhaav-gemma3-4B:Q8_0

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 alifzl/zhaav-gemma3-4B:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf alifzl/zhaav-gemma3-4B:Q8_0

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 alifzl/zhaav-gemma3-4B:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf alifzl/zhaav-gemma3-4B:Q8_0

Use Docker

docker model run hf.co/alifzl/zhaav-gemma3-4B:Q8_0

LM Studio
Jan

vLLM

How to use alifzl/zhaav-gemma3-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alifzl/zhaav-gemma3-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alifzl/zhaav-gemma3-4B",
		"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/alifzl/zhaav-gemma3-4B:Q8_0

SGLang

How to use alifzl/zhaav-gemma3-4B 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 "alifzl/zhaav-gemma3-4B" \
    --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": "alifzl/zhaav-gemma3-4B",
		"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 "alifzl/zhaav-gemma3-4B" \
        --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": "alifzl/zhaav-gemma3-4B",
		"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 alifzl/zhaav-gemma3-4B with Ollama:
```
ollama run hf.co/alifzl/zhaav-gemma3-4B:Q8_0
```

Unsloth Studio

How to use alifzl/zhaav-gemma3-4B 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 alifzl/zhaav-gemma3-4B 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 alifzl/zhaav-gemma3-4B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for alifzl/zhaav-gemma3-4B to start chatting

Docker Model Runner
How to use alifzl/zhaav-gemma3-4B with Docker Model Runner:
```
docker model run hf.co/alifzl/zhaav-gemma3-4B:Q8_0
```

Lemonade

How to use alifzl/zhaav-gemma3-4B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull alifzl/zhaav-gemma3-4B:Q8_0

Run and chat with the model

lemonade run user.zhaav-gemma3-4B-Q8_0

List all available models

lemonade list

zhaav-gemma3-4B

The alifzl/zhaav-gemma3-4B_q8_0.gguf model is a Persian specific model, fine tuned based on the Gemma 3 architecture. By utilizing QLoRA’s 4-bit quantization, it reduces computational demands while delivering strong performance in generating and understanding Persian text. Thus it is suitable for running on commodity hardware with no GPUs.

Usage

This model is compatible with both the Hugging Face Transformers library and Ollama.

Running with Ollama

ollama run hf.co/alifzl/zhaav-gemma3-4B:Q8_0

Running with Hugging Face Transformers

Install Dependencies:

pip install git+https://github.com/huggingface/transformers@v4.49.0-Gemma-3 accelerate

Load Model and Tokenizer:

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "alifzl/zhaav-gemma3-4B_q8_0.gguf"

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",  # Use "cuda" for GPU usage if available
    torch_dtype=torch.bfloat16,  # Alternatively, use torch.float16
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [
    {
        "role": "user",
        "content": "تفاوت قهوه موکا با آمریکانو چیه؟"
    }
]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True, tokenize=True, return_tensors="pt"
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training Data and Fine-Tuning

Training Dataset

Fine-Tuning was made via mshojaei77/Persian_sft dataset, which contains approximately 680k rows of Persian text focused on instruction-following and conversational interactions.

Fine-Tuning

Method: Supervised Fine-Tuning (SFT) using QLoRA (4-bit quantization)
Hardware: one T4 GPU
Software: Utilizes Hugging Face Transformers, with supporting libraries like peft for QLoRA and bitsandbytes for quantization

Evaluation Results

Metric	Value
Avg.	22.04
IFEval (0-Shot)	43.58
BBH (3-Shot)	31.87
MATH Lvl 5 (4-Shot)	11.10
GPQA (0-shot)	6.49
MuSR (0-shot)	9.49
MMLU-PRO (5-shot)	29.70

Future Work

Additional evaluation metrics and benchmarks
Expanded documentation and usage examples

Downloads last month: 36

Safetensors

Model size

4B params

Tensor type

F32

Model tree for alifzl/zhaav-gemma3-4B

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Quantized

(462)

this model

Quantizations

1 model

alifzl
/

zhaav-gemma3-4B