Instructions to use google/gemma-4-31B-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/gemma-4-31B-it with Transformers:

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

pipe = pipeline("image-text-to-text", model="google/gemma-4-31B-it")
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("google/gemma-4-31B-it")
model = AutoModelForMultimodalLM.from_pretrained("google/gemma-4-31B-it", device_map="auto")
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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
AMD Developer Cloud
Local Apps Settings

vLLM

How to use google/gemma-4-31B-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/gemma-4-31B-it"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "google/gemma-4-31B-it",
		"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/google/gemma-4-31B-it

SGLang

How to use google/gemma-4-31B-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 "google/gemma-4-31B-it" \
    --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": "google/gemma-4-31B-it",
		"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 "google/gemma-4-31B-it" \
        --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": "google/gemma-4-31B-it",
		"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 google/gemma-4-31B-it with Docker Model Runner:
```
docker model run hf.co/google/gemma-4-31B-it
```

fix(chat_template): emit tool_response multimodal placeholders inside the block

#140

by leeesangwon - opened 21 days ago

base: refs/heads/main

←

from: refs/pr/140

Discussion Files changed

+18

-22

Files changed (1) hide show

chat_template.jinja +18 -22

chat_template.jinja CHANGED Viewed

@@ -174,6 +174,23 @@
             {%- if not loop.last %},{% endif -%}
         {%- endfor -%}
         {{- '}' -}}
     {%- else -%}
         {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
     {%- endif -%}
@@ -292,28 +309,7 @@
                         {%- endfor -%}
                         {#- Handle content as string or content-parts array -#}
                         {%- set tool_body = follow.get('content') -%}
-                        {%- if tool_body is string -%}
-                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
-                        {%- elif tool_body is sequence and tool_body is not string -%}
-                            {%- set ns_txt = namespace(s='') -%}
-                            {%- for part in tool_body -%}
-                                {%- if part.get('type') == 'text' -%}
-                                    {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
-                                {%- endif -%}
-                            {%- endfor -%}
-                            {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
-                            {%- for part in tool_body -%}
-                                {%- if part.get('type') in ['image', 'image_url'] -%}
-                                    {{- '<|image|>' -}}
-                                {%- elif part.get('type') in ['audio', 'input_audio'] -%}
-                                    {{- '<|audio|>' -}}
-                                {%- elif part.get('type') == 'video' -%}
-                                    {{- '<|video|>' -}}
-                                {%- endif -%}
-                            {%- endfor -%}
-                        {%- else -%}
-                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
-                        {%- endif -%}
                         {%- set ns_tr_out.flag = true -%}
                         {%- set ns.prev_message_type = 'tool_response' -%}
                     {%- endif -%}

             {%- if not loop.last %},{% endif -%}
         {%- endfor -%}
         {{- '}' -}}
+    {%- elif response is string -%}
+        {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
+    {%- elif response is sequence -%}
+        {%- set ns_tr = namespace(txt='', mm='') -%}
+        {%- for part in response -%}
+            {%- if part.get('type') == 'text' -%}
+                {%- set ns_tr.txt = ns_tr.txt + (part.get('text') | default('')) -%}
+            {%- elif part.get('type') in ['image', 'image_url'] -%}
+                {%- set ns_tr.mm = ns_tr.mm + '<|image|>' -%}
+            {%- elif part.get('type') in ['audio', 'input_audio'] -%}
+                {%- set ns_tr.mm = ns_tr.mm + '<|audio|>' -%}
+            {%- elif part.get('type') == 'video' -%}
+                {%- set ns_tr.mm = ns_tr.mm + '<|video|>' -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {{- 'response:' + tool_name + '{value:' + format_argument(ns_tr.txt, escape_keys=False) + '}' -}}
+        {{- ns_tr.mm -}}
     {%- else -%}
         {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
     {%- endif -%}
                         {%- endfor -%}
                         {#- Handle content as string or content-parts array -#}
                         {%- set tool_body = follow.get('content') -%}
+                        {{- format_tool_response_block(ns_tname.name, tool_body) -}}
                         {%- set ns_tr_out.flag = true -%}
                         {%- set ns.prev_message_type = 'tool_response' -%}
                     {%- endif -%}