Instructions to use google/gemma-4-31B-it-qat-q4_0-unquantized-assistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/gemma-4-31B-it-qat-q4_0-unquantized-assistant 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-qat-q4_0-unquantized-assistant")
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 AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-4-31B-it-qat-q4_0-unquantized-assistant")
model = AutoModelForCausalLM.from_pretrained("google/gemma-4-31B-it-qat-q4_0-unquantized-assistant", 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 = 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 Settings

vLLM

How to use google/gemma-4-31B-it-qat-q4_0-unquantized-assistant 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-qat-q4_0-unquantized-assistant"
# 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-qat-q4_0-unquantized-assistant",
		"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-qat-q4_0-unquantized-assistant

SGLang

How to use google/gemma-4-31B-it-qat-q4_0-unquantized-assistant 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-qat-q4_0-unquantized-assistant" \
    --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-qat-q4_0-unquantized-assistant",
		"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-qat-q4_0-unquantized-assistant" \
        --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-qat-q4_0-unquantized-assistant",
		"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-qat-q4_0-unquantized-assistant with Docker Model Runner:
```
docker model run hf.co/google/gemma-4-31B-it-qat-q4_0-unquantized-assistant
```

Add response_template to tokenizer_config.json

by Rocketknight1 HF Staff - opened 25 days ago

base: refs/heads/main

←

from: refs/pr/6

Discussion Files changed

+50

-4

Files changed (2) hide show

README.md +4 -4
tokenizer_config.json +46 -0

README.md CHANGED Viewed

@@ -180,7 +180,7 @@ outputs = model.generate(**inputs, max_new_tokens=1024)
 response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
 # Parse output
-processor.parse_response(response)
 ```
 To enable reasoning, set `enable_thinking=True` and the `parse_response` function will take care of parsing the thinking output.
@@ -240,7 +240,7 @@ outputs = model.generate(**inputs, max_new_tokens=512)
 response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
 # Parse output
-processor.parse_response(response)
 ```
 </details>
@@ -298,7 +298,7 @@ outputs = model.generate(**inputs, max_new_tokens=512)
 response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
 # Parse output
-processor.parse_response(response)
 ```
 </details>
@@ -357,7 +357,7 @@ outputs = model.generate(**inputs, max_new_tokens=512)
 response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
 # Parse output
-processor.parse_response(response)
 ```
 </details>

 response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
 # Parse output
+processor.parse_response(response, prefix=inputs["input_ids"])
 ```
 To enable reasoning, set `enable_thinking=True` and the `parse_response` function will take care of parsing the thinking output.
 response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
 # Parse output
+processor.parse_response(response, prefix=inputs["input_ids"])
 ```
 </details>
 response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
 # Parse output
+processor.parse_response(response, prefix=inputs["input_ids"])
 ```
 </details>
 response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
 # Parse output
+processor.parse_response(response, prefix=inputs["input_ids"])
 ```
 </details>

tokenizer_config.json CHANGED Viewed

@@ -60,6 +60,52 @@
     "type": "object",
     "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
   },
   "soc_token": "<|channel>",
   "sot_token": "<|turn>",
   "stc_token": "<|tool_call>",

     "type": "object",
     "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
   },
+  "response_template": {
+    "defaults": {
+      "role": "assistant"
+    },
+    "fields": {
+      "content": {
+        "close": [
+          "<turn|>",
+          "<|tool_response>",
+          "<eos>"
+        ],
+        "content": "text"
+      },
+      "thinking": {
+        "close": "<channel|>",
+        "content": "text",
+        "open": "<|channel>thought\n"
+      },
+      "tool_calls": {
+        "close": "<tool_call|>",
+        "content": "json",
+        "content_args": {
+          "string_delims": [
+            [
+              "<|\"|>",
+              "<|\"|>"
+            ]
+          ],
+          "unquoted_keys": true
+        },
+        "open_pattern": "<\\|tool_call>call:(?P<name>\\w+)",
+        "repeats": true,
+        "transform": {
+          "function": {
+            "arguments": "{content}",
+            "name": "{name}"
+          },
+          "type": "function"
+        }
+      }
+    },
+    "start_anchor": [
+      "<|turn>model\n",
+      "<tool_response|>"
+    ]
+  },
   "soc_token": "<|channel>",
   "sot_token": "<|turn>",
   "stc_token": "<|tool_call>",