Instructions to use bRadu/translategemma-4b-it-novision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bRadu/translategemma-4b-it-novision with Transformers:

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

pipe = pipeline("text-generation", model="bRadu/translategemma-4b-it-novision")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bRadu/translategemma-4b-it-novision")
model = AutoModelForCausalLM.from_pretrained("bRadu/translategemma-4b-it-novision")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bRadu/translategemma-4b-it-novision with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bRadu/translategemma-4b-it-novision"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bRadu/translategemma-4b-it-novision",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bRadu/translategemma-4b-it-novision

SGLang

How to use bRadu/translategemma-4b-it-novision 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 "bRadu/translategemma-4b-it-novision" \
    --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": "bRadu/translategemma-4b-it-novision",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "bRadu/translategemma-4b-it-novision" \
        --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": "bRadu/translategemma-4b-it-novision",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bRadu/translategemma-4b-it-novision with Docker Model Runner:
```
docker model run hf.co/bRadu/translategemma-4b-it-novision
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

bRadu/translategemma-4b-it-novision

Text-only (no-vision) conversion of google/translategemma-4b-it, saved in FP16 (safetensors). The tokenizer is set from google/gemma-3-1b-it.

What this is

This repo contains a converted Gemma3ForCausalLM checkpoint extracted from the language component of the original multimodal model:

Source: google/translategemma-4b-it
Target architecture: Gemma3ForCausalLM (text-only)
Precision: float16 weights
Removed components: vision tower / multimodal-only parts

Intended use

Translation and text generation with the same chat-format style expected by TranslateGemma.
Efficient local or server inference where vision capability is not needed.

Recommended system prompt (see https://arxiv.org/pdf/2601.09012 for src codes)

SYSTEM_PROMPT = """You are a professional {source_lang} ({src_lang_code}) to {target_lang}
({tgt_lang_code}) translator. Your goal is to accurately convey the meaning and
nuances of the original {source_lang} text while adhering to {target_lang} grammar,
vocabulary, and cultural sensitivities. Produce only the {target_lang}
translation, without any additional explanations or commentary. Please translate
the following {source_lang} text into {target_lang}:\n"""

How to use (different chat template from the original `google/translategemma-4b-it` page, similar to `google/gemma-3-1b-it`)

messages = [
  {
    "role" : "system",
    "content": SYSTEM_PROMPT
  },
  {
    "role": "user",
    "content": <TEXT_TO_BE_TRANSLATED>
  }
]

from unsloth import FastModel

model, tokenizer = FastModel.from_pretrained(model)

tokenizer.apply_chat_template(messages)

Downloads last month: 9

Safetensors

Model size

4B params

Tensor type

F16

Model tree for bRadu/translategemma-4b-it-novision

Base model

google/translategemma-4b-it

Finetuned

(17)

this model

Quantizations

1 model

Paper for bRadu/translategemma-4b-it-novision

TranslateGemma Technical Report

Paper • 2601.09012 • Published Jan 13 • 22