Instructions to use trl-internal-testing/tiny-Gemma3ForConditionalGeneration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trl-internal-testing/tiny-Gemma3ForConditionalGeneration with Transformers:

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

pipe = pipeline("image-text-to-text", model="trl-internal-testing/tiny-Gemma3ForConditionalGeneration")
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("trl-internal-testing/tiny-Gemma3ForConditionalGeneration")
model = AutoModelForImageTextToText.from_pretrained("trl-internal-testing/tiny-Gemma3ForConditionalGeneration")
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 trl-internal-testing/tiny-Gemma3ForConditionalGeneration with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trl-internal-testing/tiny-Gemma3ForConditionalGeneration"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trl-internal-testing/tiny-Gemma3ForConditionalGeneration",
		"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/trl-internal-testing/tiny-Gemma3ForConditionalGeneration

SGLang

How to use trl-internal-testing/tiny-Gemma3ForConditionalGeneration 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 "trl-internal-testing/tiny-Gemma3ForConditionalGeneration" \
    --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": "trl-internal-testing/tiny-Gemma3ForConditionalGeneration",
		"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 "trl-internal-testing/tiny-Gemma3ForConditionalGeneration" \
        --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": "trl-internal-testing/tiny-Gemma3ForConditionalGeneration",
		"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 trl-internal-testing/tiny-Gemma3ForConditionalGeneration with Docker Model Runner:
```
docker model run hf.co/trl-internal-testing/tiny-Gemma3ForConditionalGeneration
```

Upload Gemma3ForConditionalGeneration

by albertvillanova HF Staff - opened Sep 17, 2025

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

-36

Files changed (3) hide show

config.json +2 -34
generation_config.json +1 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -3,6 +3,7 @@
     "Gemma3ForConditionalGeneration"
   ],
   "boi_token_index": 255999,
   "eoi_token_index": 256000,
   "eos_token_id": [
     1,
@@ -24,38 +25,6 @@
     "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"
     ],
@@ -76,8 +45,7 @@
     "use_cache": true,
     "vocab_size": 262208
   },
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.56.0.dev0",
   "vision_config": {
     "attention_dropout": 0.0,
     "hidden_act": "gelu_pytorch_tanh",

     "Gemma3ForConditionalGeneration"
   ],
   "boi_token_index": 255999,
+  "dtype": "bfloat16",
   "eoi_token_index": 256000,
   "eos_token_id": [
     1,
     "initializer_range": 0.02,
     "intermediate_size": 10240,
     "layer_types": [
       "sliding_attention",
       "sliding_attention"
     ],
     "use_cache": true,
     "vocab_size": 262208
   },
+  "transformers_version": "4.56.1",
   "vision_config": {
     "attention_dropout": 0.0,
     "hidden_act": "gelu_pytorch_tanh",

generation_config.json CHANGED Viewed

@@ -6,5 +6,5 @@
     106
   ],
   "pad_token_id": 0,
-  "transformers_version": "4.56.0.dev0"
 }

     106
   ],
   "pad_token_id": 0,
+  "transformers_version": "4.56.1"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf90459fa823642f18860212325d52bc76a2e0e520e70ab88d56d132396d673f
 size 11287536

 version https://git-lfs.github.com/spec/v1
+oid sha256:56dc37066c675420391d220a2ed601068b2eb092ed96d8e8d2ba4cd1f9de8e97
 size 11287536