Instructions to use ml-intern-explorers/gemma-4-e2b-arabic-english-vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ml-intern-explorers/gemma-4-e2b-arabic-english-vision with Transformers:

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

pipe = pipeline("image-text-to-text", model="ml-intern-explorers/gemma-4-e2b-arabic-english-vision")
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("ml-intern-explorers/gemma-4-e2b-arabic-english-vision")
model = AutoModelForImageTextToText.from_pretrained("ml-intern-explorers/gemma-4-e2b-arabic-english-vision")
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

vLLM

How to use ml-intern-explorers/gemma-4-e2b-arabic-english-vision with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ml-intern-explorers/gemma-4-e2b-arabic-english-vision"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ml-intern-explorers/gemma-4-e2b-arabic-english-vision",
		"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/ml-intern-explorers/gemma-4-e2b-arabic-english-vision

SGLang

How to use ml-intern-explorers/gemma-4-e2b-arabic-english-vision 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 "ml-intern-explorers/gemma-4-e2b-arabic-english-vision" \
    --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": "ml-intern-explorers/gemma-4-e2b-arabic-english-vision",
		"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 "ml-intern-explorers/gemma-4-e2b-arabic-english-vision" \
        --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": "ml-intern-explorers/gemma-4-e2b-arabic-english-vision",
		"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 ml-intern-explorers/gemma-4-e2b-arabic-english-vision with Docker Model Runner:
```
docker model run hf.co/ml-intern-explorers/gemma-4-e2b-arabic-english-vision
```

gemma-4-e2b-arabic-english-vision / README.md

loay

Add README

12c4de9 verified 11 days ago

preview code

raw

history blame contribute delete

2.84 kB

metadata

license: apache-2.0
language:
  - ar
  - en
base_model:
  - google/gemma-4-e2b-it
tags:
  - gemma4
  - image-text-to-text
  - arabic
  - english
  - pruned
  - vision
  - multilingual
library_name: transformers
pipeline_tag: image-text-to-text

Gemma 4 E2B — Arabic + English Vision (Pruned)

A pruned version of google/gemma-4-e2b-it optimized for Arabic and English vision-language tasks. Unnecessary language tokens and the audio encoder have been removed, resulting in a smaller and more efficient model while retaining full vision and text generation capabilities.

What was done

Component	Original	Pruned
Vocabulary	262,144 tokens	209,836 tokens (Arabic + English + special)
Vision encoder	✅ 16 layers	✅ KEPT
Audio encoder	✅ 12 layers	❌ Removed
Decoder layers	35 layers	35 layers (untouched)
PLE tables	262,144 × 256 × 35	209,836 × 256 × 35
Total size (bf16)	10.2 GB	8.5 GB
Size reduction	—	17%

Token breakdown

Arabic tokens kept: 8,460
English/Latin tokens kept: 201,096
Special tokens: 24
Byte fallbacks: 256
Total kept: 209,836 (80.0% of original)
Dropped: 52,308 (CJK, Cyrillic, Devanagari, Thai, etc.)

Why this exists

Gemma 4's Per-Layer Embedding (PLE) architecture stores a separate embedding table for each of its 35 decoder layers. With 262K vocab, that's 4.7 GB of PLE tables alone (53% of the model). By pruning to Arabic+English only, we cut this to ~3.8 GB.

The vision encoder is kept intact for image understanding tasks.

Benchmark: Arabic text recognition (zero-shot, no fine-tuning)

Evaluated on loay/ar_stage1_probe — 100 samples, seed=42:

Model	Params	VRAM	CER ↓	Exact Match
This model (pruned)	4.25B	8.5 GB	0.1168	23/100
google/gemma-4-e2b-it (original)	5.10B	10.2 GB	0.1168	23/100

Identical output on all 100 samples — pruning is lossless for Arabic+English tasks.

Intended use

Arabic + English vision-language tasks
Document understanding
Fine-tuning base for bilingual Arabic/English applications
Any task where CJK/Cyrillic/Indic language support is not needed

Usage

from transformers import AutoModelForImageTextToText, AutoProcessor

model = AutoModelForImageTextToText.from_pretrained(
    "ml-agent-explorers/gemma-4-e2b-arabic-english-vision",
    dtype="bfloat16",
    device_map="auto",
)
processor = AutoProcessor.from_pretrained(
    "ml-agent-explorers/gemma-4-e2b-arabic-english-vision"
)

Base model

google/gemma-4-e2b-it