Spaces:
Running on Zero
Running on Zero
|
Download README.md from hugging-apps/clairic-flash: direct link, hf CLI and curl.
- Browser
- Download file 992 Bytes
-
https://huggingface.co/spaces/hugging-apps/clairic-flash/resolve/main/README.md
- Command line
-
hf download hf://spaces/hugging-apps/clairic-flash/README.md
-
curl -L -o README.md https://huggingface.co/spaces/hugging-apps/clairic-flash/resolve/main/README.md
992 Bytes
metadata
title: Clairic Flash
emoji: ⚡
colorFrom: yellow
colorTo: blue
sdk: gradio
sdk_version: 6.32.0
app_file: app.py
short_description: Cloudflare Clairic Flash 9B typed structured extraction
python_version: '3.12'
startup_duration_timeout: 1h
models:
- Cloudflare/clairic-flash
Clairic Flash · System One: Extract
Gradio demo for Cloudflare/clairic-flash, a 9B multimodal model (Qwen3.5-9B base + typed output head) that turns a text/JSON state (and optional images) plus a schema of typed fields into structured, scored answers (confidence, p_null, optional quantiles).
Runs on ZeroGPU. The release runtime's Hopper-only kernels (FA3, DeepGEMM, FlashInfer RMSNorm, CUDA-graph decode) are replaced by SDPA and numerically equivalent PyTorch ops so it runs on Blackwell sm_120.
Example receipt images come from the CORD-v2 dataset by NAVER Clova AI, licensed CC-BY-4.0.