Instructions to use ClinicalIntelligence/saama_gemma with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ClinicalIntelligence/saama_gemma with Transformers:

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

pipe = pipeline("image-text-to-text", model="ClinicalIntelligence/saama_gemma")
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("ClinicalIntelligence/saama_gemma")
model = AutoModelForMultimodalLM.from_pretrained("ClinicalIntelligence/saama_gemma", 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 ClinicalIntelligence/saama_gemma with vLLM:

Install from pip and serve model

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

SGLang

How to use ClinicalIntelligence/saama_gemma 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 "ClinicalIntelligence/saama_gemma" \
    --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": "ClinicalIntelligence/saama_gemma",
		"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 "ClinicalIntelligence/saama_gemma" \
        --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": "ClinicalIntelligence/saama_gemma",
		"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 ClinicalIntelligence/saama_gemma with Docker Model Runner:
```
docker model run hf.co/ClinicalIntelligence/saama_gemma
```

praveenramesh commited on Feb 24

Commit

c7cc2d1

verified ·

1 Parent(s): 2018c10

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -13

README.md CHANGED Viewed

@@ -26,6 +26,19 @@ import re
 from transformers import pipeline
 def extract_entities(text):
     """
@@ -55,19 +68,6 @@ def extract_entities(text):
     return extracted_data
-prefix = """Extract SDTM domain entities from: """
-unstructured_text = """<ENTER YOUR TEXT HERE>"""
-generator = pipeline(
-    "text-generation", model="ClinicalIntelligence/saama_gemma", device="cuda"
-)
-output = generator(
-    [{"role": "user", "content": prefix + unstructured_text}],
-    max_new_tokens=16000,
-    return_full_text=False,
-)[0]
-llm_output = output["generated_text"]
 extracted_entities_list = extract_entities(llm_output)
 for extracted_entity in extracted_entities_list:

 from transformers import pipeline
+prefix = """Extract SDTM domain entities from: """
+unstructured_text = """<ENTER YOUR TEXT HERE>"""
+generator = pipeline(
+    "text-generation", model="ClinicalIntelligence/saama_gemma", device="cuda"
+)
+output = generator(
+    [{"role": "user", "content": prefix + unstructured_text}],
+    return_full_text=False,
+)[0]
+llm_output = output["generated_text"]
 def extract_entities(text):
     """
     return extracted_data
 extracted_entities_list = extract_entities(llm_output)
 for extracted_entity in extracted_entities_list: