Image-Text-to-Text
Transformers
Safetensors
qwen3_5
quantized
decision-model
conversational
compressed-tensors
Instructions to use Level5Tech/clef-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Level5Tech/clef-FP8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Level5Tech/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("Level5Tech/clef-FP8") model = AutoModelForMultimodalLM.from_pretrained("Level5Tech/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 Level5Tech/clef-FP8 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Level5Tech/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": "Level5Tech/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/Level5Tech/clef-FP8
- SGLang
How to use Level5Tech/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 "Level5Tech/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": "Level5Tech/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 "Level5Tech/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": "Level5Tech/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 Level5Tech/clef-FP8 with Docker Model Runner:
docker model run hf.co/Level5Tech/clef-FP8
Commit ·
3031c4c
1
Parent(s): 31c1eb1
Link the collection and the Zenodo archive, add the citation (#3)
Browse files- Link the collection and the Zenodo archive, add the citation (2928ec00e82ca57cfc1ad3534f642ae8324d60fc)
README.md
CHANGED
|
@@ -19,4 +19,22 @@ Paper: https://arxiv.org/abs/2611.15671
|
|
| 19 |
|
| 20 |
Measurements, recipes and per-record outputs: https://github.com/Level5Tech/clef-quant-bench
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
The base model is under Apache-2.0. Its LICENSE is included here, and NOTICE says these weights were modified by quantization.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
Measurements, recipes and per-record outputs: https://github.com/Level5Tech/clef-quant-bench
|
| 21 |
|
| 22 |
+
The paper and all six builds, in one collection: https://huggingface.co/collections/Level5Tech/the-noise-floor-of-a-quantization-comparison-6afd62e8288cc5e14becefaf
|
| 23 |
+
|
| 24 |
+
Archived release (all versions): https://doi.org/10.5281/zenodo.24184497
|
| 25 |
+
|
| 26 |
The base model is under Apache-2.0. Its LICENSE is included here, and NOTICE says these weights were modified by quantization.
|
| 27 |
+
|
| 28 |
+
## Citation
|
| 29 |
+
|
| 30 |
+
```bibtex
|
| 31 |
+
@misc{blagojevich2026noisefloorquantizationcomparison,
|
| 32 |
+
title={The Noise Floor of a Quantization Comparison: Engine, restart, batch and kernel drift, measured against 8-bit and 4-bit effects in two decision models},
|
| 33 |
+
author={Aleks Blagojevich and Trevor Sunderland},
|
| 34 |
+
year={2026},
|
| 35 |
+
eprint={2611.15671},
|
| 36 |
+
archivePrefix={arXiv},
|
| 37 |
+
primaryClass={cs.LG},
|
| 38 |
+
url={https://arxiv.org/abs/2611.15671},
|
| 39 |
+
}
|
| 40 |
+
```
|