Instructions to use Cloudflare/clef-flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Cloudflare/clef-flash with Transformers:

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

pipe = pipeline("image-text-to-text", model="Cloudflare/clef-flash")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Cloudflare/clef-flash")
model = AutoModelForMultimodalLM.from_pretrained("Cloudflare/clef-flash", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Cloudflare/clef-flash with vLLM:

Install from pip and serve model

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

SGLang

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

areneau commited on 19 days ago

Commit

e8ad11d

verified ·

1 Parent(s): 042498e

Update model card and code docstrings

Browse files

Files changed (2) hide show

README.md +6 -6
joint_schema_model.py +2 -2

README.md CHANGED Viewed

@@ -16,15 +16,15 @@ tags:
 - custom-code
 ---
-# CLEF-Flash
-CLEF-Flash is a 9B multimodal model that turns a state and a schema of typed
 questions into decisions. It reads the state as text, JSON, images, or video, and returns a
 probability for every allowed option of every question in a single forward pass. There is no
 free-form text generation and no output parsing.
-CLEF-Flash is post-trained from [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B). See
-[CLEF](https://huggingface.co/Cloudflare/clef) for the
 larger variant.
 ## Model
@@ -126,7 +126,7 @@ Each question has:
 ### Decision Index
-Per-benchmark results on the Decision Index 0.2.1 suite. Scores are percentages; ForecastBench is a Brier score, where lower is better. The best score in each row is in bold. This is a partial, unofficial run: HLE was not run, so no aggregate Decision Index score is reported.
 | # | Benchmark | Clef | Clef-flash | Jev | DiffusionGemma Jev | Kev 9B | Laya |
 |---|---|---|---|---|---|---|---|
@@ -174,7 +174,7 @@ Per-benchmark results on the Decision Index 0.2.1 suite. Scores are percentages;
 ### Workflow evals
-Decision accuracy on four end-to-end business workflows, scored against consensus reference labels. All models are scored on the same dataset revision and case cohort.
 | Workflow | Metric | Cases | Clef | Clef-flash | Jev |
 |---|---|---:|---:|---:|---:|

 - custom-code
 ---
+# Clef-Flash
+Clef-Flash is a 9B multimodal model that turns a state and a schema of typed
 questions into decisions. It reads the state as text, JSON, images, or video, and returns a
 probability for every allowed option of every question in a single forward pass. There is no
 free-form text generation and no output parsing.
+Clef-Flash is post-trained from [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B). See
+[Clef](https://huggingface.co/Cloudflare/clef) for the
 larger variant.
 ## Model
 ### Decision Index
+Per-benchmark results from our internal run of the [Decision Index](https://huggingface.co/spaces/multimodalart/jev-decision-index) 0.2.1 suite. Scores are percentages; ForecastBench is a Brier score, where lower is better. The best score in each row is in bold.
 | # | Benchmark | Clef | Clef-flash | Jev | DiffusionGemma Jev | Kev 9B | Laya |
 |---|---|---|---|---|---|---|---|
 ### Workflow evals
+Decision accuracy on four end-to-end business workflows from [Typesafe Evals](https://evals.typesafe.ai/), scored against consensus reference labels. All models are scored on the same dataset revision and case cohort.
 | Workflow | Metric | Cases | Clef | Clef-flash | Jev |
 |---|---|---:|---:|---:|---:|

joint_schema_model.py CHANGED Viewed

@@ -1,4 +1,4 @@
-"""CLEF: a multimodal Qwen backbone with a joint schema head for typed decisions.
 A record provides a ``state`` (any JSON value), optional ``images`` and ``videos``,
 and ``questions``. Each question has a ``type`` (``noul``, ``choice``, or ``score``),
@@ -492,7 +492,7 @@ def load_release_model(
     dtype: torch.dtype = torch.bfloat16,
     **from_pretrained_kwargs: Any,
 ) -> tuple[ClefModel, Any]:
-    """Load a CLEF release (merged backbone, joint schema head, and processor)."""
     from huggingface_hub import snapshot_download
     from safetensors.torch import load_file
     from transformers import AutoProcessor, Qwen3_5ForConditionalGeneration

+"""Clef: a multimodal Qwen backbone with a joint schema head for typed decisions.
 A record provides a ``state`` (any JSON value), optional ``images`` and ``videos``,
 and ``questions``. Each question has a ``type`` (``noul``, ``choice``, or ``score``),
     dtype: torch.dtype = torch.bfloat16,
     **from_pretrained_kwargs: Any,
 ) -> tuple[ClefModel, Any]:
+    """Load a Clef release (merged backbone, joint schema head, and processor)."""
     from huggingface_hub import snapshot_download
     from safetensors.torch import load_file
     from transformers import AutoProcessor, Qwen3_5ForConditionalGeneration