Instructions to use alwaysgood/gemma4-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alwaysgood/gemma4-it with Transformers:

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

pipe = pipeline("image-text-to-text", model="alwaysgood/gemma4-it")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("alwaysgood/gemma4-it")
model = AutoModelForImageTextToText.from_pretrained("alwaysgood/gemma4-it")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use alwaysgood/gemma4-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alwaysgood/gemma4-it"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alwaysgood/gemma4-it",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/alwaysgood/gemma4-it

SGLang

How to use alwaysgood/gemma4-it 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 "alwaysgood/gemma4-it" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alwaysgood/gemma4-it",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "alwaysgood/gemma4-it" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alwaysgood/gemma4-it",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use alwaysgood/gemma4-it 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 alwaysgood/gemma4-it 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 alwaysgood/gemma4-it to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for alwaysgood/gemma4-it to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="alwaysgood/gemma4-it",
    max_seq_length=2048,
)

Docker Model Runner
How to use alwaysgood/gemma4-it with Docker Model Runner:
```
docker model run hf.co/alwaysgood/gemma4-it
```

gemma4-it / tokenizer_config.json

alwaysgood

Upload final model from sft-gemma4-cpt-stage2-reversed

7a09822 verified 27 days ago

raw

history blame contribute delete

1.48 kB

	{
	"audio_token": "<\|audio\|>",
	"backend": "tokenizers",
	"boa_token": "<\|audio>",
	"boi_token": "<\|image>",
	"bos_token": "<bos>",
	"eoa_token": "<audio\|>",
	"eoc_token": "<channel\|>",
	"eoi_token": "<image\|>",
	"eos_token": "<eos>",
	"eot_token": "<turn\|>",
	"escape_token": "<\|\"\|>",
	"etc_token": "<tool_call\|>",
	"etd_token": "<tool\|>",
	"etr_token": "<tool_response\|>",
	"extra_special_tokens": [],
	"image_token": "<\|image\|>",
	"is_local": false,
	"mask_token": "<mask>",
	"model_max_length": 1000000000000000019884624838656,
	"model_specific_special_tokens": {
	"audio_token": "<\|audio\|>",
	"boa_token": "<\|audio>",
	"boi_token": "<\|image>",
	"eoa_token": "<audio\|>",
	"eoc_token": "<channel\|>",
	"eoi_token": "<image\|>",
	"eot_token": "<turn\|>",
	"escape_token": "<\|\"\|>",
	"etc_token": "<tool_call\|>",
	"etd_token": "<tool\|>",
	"etr_token": "<tool_response\|>",
	"image_token": "<\|image\|>",
	"soc_token": "<\|channel>",
	"sot_token": "<\|turn>",
	"stc_token": "<\|tool_call>",
	"std_token": "<\|tool>",
	"str_token": "<\|tool_response>",
	"think_token": "<\|think\|>"
	},
	"pad_token": "<pad>",
	"padding_side": "left",
	"processor_class": "Gemma4Processor",
	"soc_token": "<\|channel>",
	"sot_token": "<\|turn>",
	"stc_token": "<\|tool_call>",
	"std_token": "<\|tool>",
	"str_token": "<\|tool_response>",
	"think_token": "<\|think\|>",
	"tokenizer_class": "GemmaTokenizer",
	"unk_token": "<unk>"
	}

	{
	"audio_token": "<\|audio\|>",
	"backend": "tokenizers",
	"boa_token": "<\|audio>",
	"boi_token": "<\|image>",
	"bos_token": "<bos>",
	"eoa_token": "<audio\|>",
	"eoc_token": "<channel\|>",
	"eoi_token": "<image\|>",
	"eos_token": "<eos>",
	"eot_token": "<turn\|>",
	"escape_token": "<\|\"\|>",
	"etc_token": "<tool_call\|>",
	"etd_token": "<tool\|>",
	"etr_token": "<tool_response\|>",
	"extra_special_tokens": [],
	"image_token": "<\|image\|>",
	"is_local": false,
	"mask_token": "<mask>",
	"model_max_length": 1000000000000000019884624838656,
	"model_specific_special_tokens": {
	"audio_token": "<\|audio\|>",
	"boa_token": "<\|audio>",
	"boi_token": "<\|image>",
	"eoa_token": "<audio\|>",
	"eoc_token": "<channel\|>",
	"eoi_token": "<image\|>",
	"eot_token": "<turn\|>",
	"escape_token": "<\|\"\|>",
	"etc_token": "<tool_call\|>",
	"etd_token": "<tool\|>",
	"etr_token": "<tool_response\|>",
	"image_token": "<\|image\|>",
	"soc_token": "<\|channel>",
	"sot_token": "<\|turn>",
	"stc_token": "<\|tool_call>",
	"std_token": "<\|tool>",
	"str_token": "<\|tool_response>",
	"think_token": "<\|think\|>"
	},
	"pad_token": "<pad>",
	"padding_side": "left",
	"processor_class": "Gemma4Processor",
	"soc_token": "<\|channel>",
	"sot_token": "<\|turn>",
	"stc_token": "<\|tool_call>",
	"std_token": "<\|tool>",
	"str_token": "<\|tool_response>",
	"think_token": "<\|think\|>",
	"tokenizer_class": "GemmaTokenizer",
	"unk_token": "<unk>"
	}