Instructions to use prithivMLmods/clef-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/clef-FP8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="prithivMLmods/clef-FP8")
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("prithivMLmods/clef-FP8")
model = AutoModelForMultimodalLM.from_pretrained("prithivMLmods/clef-FP8", 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 prithivMLmods/clef-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/clef-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/clef-FP8",
		"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/prithivMLmods/clef-FP8

SGLang

How to use prithivMLmods/clef-FP8 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 "prithivMLmods/clef-FP8" \
    --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": "prithivMLmods/clef-FP8",
		"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 "prithivMLmods/clef-FP8" \
        --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": "prithivMLmods/clef-FP8",
		"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 prithivMLmods/clef-FP8 with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/clef-FP8
```

prithivMLmods commited on 5 days ago

Commit

cea2293

verified ·

1 Parent(s): ddffd9e

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -9

README.md CHANGED Viewed

@@ -11,6 +11,8 @@ tags:
 - llm-compressor
 - vllm
 - clef
 - cloudflare
 - systemone
 - qwen3.8
@@ -141,15 +143,6 @@ processor.save_pretrained(dst)
 Then copy these files from the original Clef repo into `clef-FP8/` unchanged:
 `joint_head.safetensors`, `joint_head_config.json`, `joint_schema_model.py`.
-## Evaluation
-I have **not** run the Decision Index or the workflow evals on this FP8 checkpoint. The numbers
-in the [Clef card](https://huggingface.co/Cloudflare/clef) are for the BF16 model and should not be
-assumed to carry over exactly. FP8 dynamic quantization is generally close to lossless, but Clef
-outputs per-option probabilities, so small shifts in calibration (confidence values) are possible
-even when the argmax decisions match. If you depend on calibrated probabilities or thresholds,
-validate on your own data before switching.
 ## Notes and limitations
 - **Joint head:** the joint schema head is stored separately and is kept in its original

 - llm-compressor
 - vllm
 - clef
+- fp8
+- w8a8
 - cloudflare
 - systemone
 - qwen3.8
 Then copy these files from the original Clef repo into `clef-FP8/` unchanged:
 `joint_head.safetensors`, `joint_head_config.json`, `joint_schema_model.py`.
 ## Notes and limitations
 - **Joint head:** the joint schema head is stored separately and is kept in its original