Instructions to use RedHatAI/gemma-4-31B-it-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/gemma-4-31B-it-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="RedHatAI/gemma-4-31B-it-NVFP4")
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("RedHatAI/gemma-4-31B-it-NVFP4")
model = AutoModelForImageTextToText.from_pretrained("RedHatAI/gemma-4-31B-it-NVFP4")
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 RedHatAI/gemma-4-31B-it-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/gemma-4-31B-it-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/gemma-4-31B-it-NVFP4",
		"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/RedHatAI/gemma-4-31B-it-NVFP4

SGLang

How to use RedHatAI/gemma-4-31B-it-NVFP4 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 "RedHatAI/gemma-4-31B-it-NVFP4" \
    --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": "RedHatAI/gemma-4-31B-it-NVFP4",
		"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 "RedHatAI/gemma-4-31B-it-NVFP4" \
        --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": "RedHatAI/gemma-4-31B-it-NVFP4",
		"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 RedHatAI/gemma-4-31B-it-NVFP4 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/gemma-4-31B-it-NVFP4
```

bdellabe commited on Apr 10

Commit

e968c10

verified ·

1 Parent(s): 0e7d4a9

Update tokenizer_config.json

Browse files

Files changed (1) hide show

tokenizer_config.json +22 -43

tokenizer_config.json CHANGED Viewed

@@ -17,72 +17,51 @@
     "<|video|>"
   ],
   "image_token": "<|image|>",
-  "is_local": false,
   "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
-  "model_specific_special_tokens": {
-    "audio_token": "<|audio|>",
-    "boa_token": "<|audio>",
-    "boi_token": "<|image>",
-    "eoa_token": "<audio|>",
-    "eoc_token": "<channel|>",
-    "eoi_token": "<image|>",
-    "eot_token": "<turn|>",
-    "escape_token": "<|\"|>",
-    "etc_token": "<tool_call|>",
-    "etd_token": "<tool|>",
-    "etr_token": "<tool_response|>",
-    "image_token": "<|image|>",
-    "soc_token": "<|channel>",
-    "sot_token": "<|turn>",
-    "stc_token": "<|tool_call>",
-    "std_token": "<|tool>",
-    "str_token": "<|tool_response>",
-    "think_token": "<|think|>"
-  },
   "pad_token": "<pad>",
   "padding_side": "left",
   "processor_class": "Gemma4Processor",
   "response_schema": {
     "properties": {
-      "content": {
-        "type": "string"
-      },
       "role": {
         "const": "assistant"
       },
       "thinking": {
         "type": "string"
       },
       "tool_calls": {
         "items": {
           "properties": {
             "function": {
               "properties": {
-                "arguments": {
-                  "additionalProperties": {},
-                  "type": "object",
-                  "x-parser": "gemma4-tool-call"
-                },
                 "name": {
                   "type": "string"
                 }
-              },
-              "type": "object",
-              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
-            },
-            "type": {
-              "const": "function"
             }
-          },
-          "type": "object"
-        },
-        "type": "array",
-        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
       }
     },
-    "type": "object",
-    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?"
   },
   "soc_token": "<|channel>",
   "sot_token": "<|turn>",
@@ -92,4 +71,4 @@
   "think_token": "<|think|>",
   "tokenizer_class": "GemmaTokenizer",
   "unk_token": "<unk>"
-}

     "<|video|>"
   ],
   "image_token": "<|image|>",
   "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "padding_side": "left",
   "processor_class": "Gemma4Processor",
   "response_schema": {
+    "type": "object",
     "properties": {
       "role": {
         "const": "assistant"
       },
       "thinking": {
         "type": "string"
       },
+      "content": {
+        "type": "string"
+      },
       "tool_calls": {
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>",
+        "type": "array",
         "items": {
+          "type": "object",
           "properties": {
+            "type": {
+              "const": "function"
+            },
             "function": {
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})",
               "properties": {
                 "name": {
                   "type": "string"
+                },
+                "arguments": {
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call",
+                  "additionalProperties": {}
                 }
+              }
             }
+          }
+        }
       }
     },
+    "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>",
   "think_token": "<|think|>",
   "tokenizer_class": "GemmaTokenizer",
   "unk_token": "<unk>"
+}