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

Libraries

How to use helviz/gemma-3-4b-it-finetune with Transformers:

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

pipe = pipeline("image-text-to-text", model="helviz/gemma-3-4b-it-finetune")
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("helviz/gemma-3-4b-it-finetune")
model = AutoModelForMultimodalLM.from_pretrained("helviz/gemma-3-4b-it-finetune")
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 helviz/gemma-3-4b-it-finetune with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="helviz/gemma-3-4b-it-finetune",
	filename="gemma-3-4b-it-finetune.Q4_K_M.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 helviz/gemma-3-4b-it-finetune 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 helviz/gemma-3-4b-it-finetune:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf helviz/gemma-3-4b-it-finetune:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/helviz/gemma-3-4b-it-finetune:Q4_K_M

LM Studio
Jan

vLLM

How to use helviz/gemma-3-4b-it-finetune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "helviz/gemma-3-4b-it-finetune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "helviz/gemma-3-4b-it-finetune",
		"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/helviz/gemma-3-4b-it-finetune:Q4_K_M

SGLang

How to use helviz/gemma-3-4b-it-finetune 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 "helviz/gemma-3-4b-it-finetune" \
    --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": "helviz/gemma-3-4b-it-finetune",
		"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 "helviz/gemma-3-4b-it-finetune" \
        --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": "helviz/gemma-3-4b-it-finetune",
		"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 helviz/gemma-3-4b-it-finetune with Ollama:
```
ollama run hf.co/helviz/gemma-3-4b-it-finetune:Q4_K_M
```

Unsloth Studio

How to use helviz/gemma-3-4b-it-finetune 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 helviz/gemma-3-4b-it-finetune 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 helviz/gemma-3-4b-it-finetune to start chatting

Using HuggingFace Spaces for Unsloth

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

Atomic Chat new
Docker Model Runner
How to use helviz/gemma-3-4b-it-finetune with Docker Model Runner:
```
docker model run hf.co/helviz/gemma-3-4b-it-finetune:Q4_K_M
```

Lemonade

How to use helviz/gemma-3-4b-it-finetune with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull helviz/gemma-3-4b-it-finetune:Q4_K_M

Run and chat with the model

lemonade run user.gemma-3-4b-it-finetune-Q4_K_M

List all available models

lemonade list

helviz commited on Jun 12

Commit

bc3e04a

verified ·

1 Parent(s): 95b1a18

(Trained with Unsloth)

Browse files

Files changed (8) hide show

.gitattributes +1 -0
chat_template.jinja +8 -0
config.json +112 -0
generation_config.json +13 -0
processor_config.json +28 -0
tokenizer.json +3 -0
tokenizer.model +3 -0
tokenizer_config.json +0 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,8 @@

+{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{'<start_of_turn>user
+' + messages[0]['content'] | trim + ' ' + messages[1]['content'] | trim + '<end_of_turn>
+'}}{% set messages = messages[2:] %}{% endif %}{% for message in messages %}{% if message['role'] == 'user' %}{{'<start_of_turn>user
+' + message['content'] | trim + '<end_of_turn>
+'}}{% elif message['role'] == 'assistant' %}{{'<start_of_turn>model
+' + message['content'] | trim + '<end_of_turn>
+' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<start_of_turn>model
+' }}{% endif %}

config.json ADDED Viewed

	@@ -0,0 +1,112 @@

+{
+    "architectures": [
+        "Gemma3ForConditionalGeneration"
+    ],
+    "boi_token_index": 255999,
+    "bos_token_id": 2,
+    "torch_dtype": "float16",
+    "eoi_token_index": 256000,
+    "eos_token_id": 106,
+    "image_token_index": 262144,
+    "initializer_range": 0.02,
+    "mm_tokens_per_image": 256,
+    "model_name": "unsloth/gemma-3-4b-it-unsloth-bnb-4bit",
+    "model_type": "gemma3",
+    "pad_token_id": 0,
+    "text_config": {
+        "_sliding_window_pattern": 6,
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attn_logit_softcapping": null,
+        "bos_token_id": 2,
+        "cache_implementation": "hybrid",
+        "torch_dtype": "float16",
+        "eos_token_id": 1,
+        "final_logit_softcapping": null,
+        "head_dim": 256,
+        "hidden_activation": "gelu_pytorch_tanh",
+        "hidden_size": 2560,
+        "initializer_range": 0.02,
+        "intermediate_size": 10240,
+        "layer_types": [
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention"
+        ],
+        "max_position_embeddings": 131072,
+        "model_type": "gemma3_text",
+        "num_attention_heads": 8,
+        "num_hidden_layers": 34,
+        "num_key_value_heads": 4,
+        "pad_token_id": 0,
+        "query_pre_attn_scalar": 256,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "full_attention": {
+                "factor": 8.0,
+                "rope_theta": 1000000.0,
+                "rope_type": "linear"
+            },
+            "sliding_attention": {
+                "rope_theta": 10000.0,
+                "rope_type": "default"
+            }
+        },
+        "sliding_window": 1024,
+        "sliding_window_pattern": 6,
+        "tie_word_embeddings": true,
+        "use_bidirectional_attention": false,
+        "use_cache": true,
+        "vocab_size": 262208
+    },
+    "tie_word_embeddings": true,
+    "unsloth_fixed": true,
+    "unsloth_version": "2026.6.5",
+    "use_cache": false,
+    "vision_config": {
+        "attention_dropout": 0.0,
+        "torch_dtype": "float16",
+        "hidden_act": "gelu_pytorch_tanh",
+        "hidden_size": 1152,
+        "image_size": 896,
+        "intermediate_size": 4304,
+        "layer_norm_eps": 1e-06,
+        "model_type": "siglip_vision_model",
+        "num_attention_heads": 16,
+        "num_channels": 3,
+        "num_hidden_layers": 27,
+        "patch_size": 14,
+        "vision_use_head": false
+    }
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,13 @@

+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.12.0"
+}

processor_config.json ADDED Viewed

	@@ -0,0 +1,28 @@

+{
+  "image_processor": {
+    "do_convert_rgb": null,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Gemma3ImageProcessor",
+    "image_seq_length": 256,
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "resample": 2,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "height": 896,
+      "width": 896
+    }
+  },
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
+size 33384567

tokenizer.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

tokenizer_config.json ADDED Viewed

The diff for this file is too large to render. See raw diff