Instructions to use RedHatAI/gemma-4-31B-it-FP8-dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/gemma-4-31B-it-FP8-dynamic 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-FP8-dynamic")
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("RedHatAI/gemma-4-31B-it-FP8-dynamic")
model = AutoModelForMultimodalLM.from_pretrained("RedHatAI/gemma-4-31B-it-FP8-dynamic", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RedHatAI/gemma-4-31B-it-FP8-dynamic 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-FP8-dynamic"
# 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-FP8-dynamic",
		"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-FP8-dynamic

SGLang

How to use RedHatAI/gemma-4-31B-it-FP8-dynamic 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-FP8-dynamic" \
    --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-FP8-dynamic",
		"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-FP8-dynamic" \
        --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-FP8-dynamic",
		"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-FP8-dynamic with Docker Model Runner:
```
docker model run hf.co/RedHatAI/gemma-4-31B-it-FP8-dynamic
```

alexmarques commited on Jun 18

Commit

da2311a

verified ·

1 Parent(s): 4675bed

Add eval results: gsm8k_platinum.json

Browse files

Files changed (1) hide show

every_eval_ever/gsm8k_platinum.json +119 -0

every_eval_ever/gsm8k_platinum.json ADDED Viewed

	@@ -0,0 +1,119 @@

+{
+  "schema_version": "0.2.2",
+  "evaluation_id": "gsm8k_platinum_cot_llama/RedHatAI/gemma-4-31B-it-FP8-Dynamic/1781644883.581219",
+  "evaluation_timestamp": "1781235616",
+  "retrieved_timestamp": "1781644883.581219",
+  "source_metadata": {
+    "source_name": "lm-evaluation-harness",
+    "source_type": "evaluation_run",
+    "source_organization_name": "RedHatAI",
+    "evaluator_relationship": "third_party"
+  },
+  "eval_library": {
+    "name": "lm_eval",
+    "version": "0.4.13.dev0"
+  },
+  "model_info": {
+    "name": "RedHatAI/gemma-4-31B-it-FP8-Dynamic",
+    "id": "RedHatAI/gemma-4-31B-it-FP8-Dynamic",
+    "developer": "RedHatAI",
+    "additional_details": {
+      "model_args": "{'model': 'RedHatAI/gemma-4-31B-it-FP8-Dynamic', 'max_length': 36096, 'base_url': 'http://127.0.0.1:8000/v1/chat/completions', 'num_concurrent': 128, 'max_retries': 3, 'tokenized_requests': False, 'tokenizer_backend': None, 'timeout': 1200}",
+      "num_seeds_merged": "3"
+    }
+  },
+  "evaluation_results": [
+    {
+      "evaluation_name": "gsm8k_platinum_cot_llama/strict-match",
+      "source_data": {
+        "dataset_name": "gsm8k_platinum_cot_llama",
+        "source_type": "hf_dataset",
+        "hf_repo": "madrylab/gsm8k-platinum",
+        "hf_split": "test"
+      },
+      "metric_config": {
+        "evaluation_description": "exact_match (filter: strict-match)",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.9583677970774745,
+        "details": {
+          "seed_scores": "[0.9586435070306039, 0.9586435070306039, 0.9578163771712159]",
+          "evaluation_timestamps": "[1781235616, 1781235679, 1781235740]",
+          "seed_values": "[1234, 2345, 3456]"
+        },
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.00027570995312931057,
+            "method": "across_seeds"
+          },
+          "num_samples": 3
+        }
+      },
+      "generation_config": {
+        "generation_args": {
+          "temperature": 1.0,
+          "top_p": 0.95,
+          "top_k": 64.0,
+          "max_tokens": 32000,
+          "max_attempts": 1
+        },
+        "additional_details": {
+          "do_sample": "true",
+          "until": "[\"<|eot_id|>\", \"<|start_header_id|>user<|end_header_id|>\", \"Q:\", \"</s>\", \"<|im_end|>\"]",
+          "seed": "1234",
+          "num_fewshot": "0"
+        }
+      }
+    },
+    {
+      "evaluation_name": "gsm8k_platinum_cot_llama/flexible-extract",
+      "source_data": {
+        "dataset_name": "gsm8k_platinum_cot_llama",
+        "source_type": "hf_dataset",
+        "hf_repo": "madrylab/gsm8k-platinum",
+        "hf_split": "test"
+      },
+      "metric_config": {
+        "evaluation_description": "exact_match (filter: flexible-extract)",
+        "lower_is_better": false,
+        "score_type": "continuous",
+        "min_score": 0.0,
+        "max_score": 1.0
+      },
+      "score_details": {
+        "score": 0.9586435070306039,
+        "details": {
+          "seed_scores": "[0.9586435070306039, 0.9586435070306039, 0.9586435070306039]",
+          "evaluation_timestamps": "[1781235616, 1781235679, 1781235740]",
+          "seed_values": "[1234, 2345, 3456]"
+        },
+        "uncertainty": {
+          "standard_error": {
+            "value": 0.0,
+            "method": "across_seeds"
+          },
+          "num_samples": 3
+        }
+      },
+      "generation_config": {
+        "generation_args": {
+          "temperature": 1.0,
+          "top_p": 0.95,
+          "top_k": 64.0,
+          "max_tokens": 32000,
+          "max_attempts": 1
+        },
+        "additional_details": {
+          "do_sample": "true",
+          "until": "[\"<|eot_id|>\", \"<|start_header_id|>user<|end_header_id|>\", \"Q:\", \"</s>\", \"<|im_end|>\"]",
+          "seed": "1234",
+          "num_fewshot": "0"
+        }
+      }
+    }
+  ]
+}