webbrain-one
/

d1-browser-decision-fp32

image-text-to-decision

Model card Files Files and versions

webbrain-one commited on 2 days ago

Commit

9023fa4

·

verified ·

1 Parent(s): 71866f0

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ tags:
 # d1 Browser Decision FP32
-An experimental, audio-free derivative of [LiquidAI/d1-omni-600M](https://huggingface.co/LiquidAI/d1-omni-600M/tree/02b55d7076f15129e59ab3f94783f32c4b088674). It directly scores named options for `choice`, `noul` and ordinal `score` questions using text/JSON state and optional screenshots. It does **not** generate text or tokens. Do not call `generate()` or treat it as a causal chat model.
 The reported quality data are authored synthetic browser pages, with AI-authored labels independently checked through AI DOM/pixel review, not human-expert annotations. Actual Chrome/WebGPU runtime parity was measured separately; that does not establish reliable completion detection on independently developed websites.

 # d1 Browser Decision FP32
+An audio-free derivative of [LiquidAI/d1-omni-600M](https://huggingface.co/LiquidAI/d1-omni-600M/tree/02b55d7076f15129e59ab3f94783f32c4b088674). It directly scores named options for `choice`, `noul` and ordinal `score` questions using text/JSON state and optional screenshots. It does **not** generate text or tokens. Do not call `generate()` or treat it as a causal chat model.
 The reported quality data are authored synthetic browser pages, with AI-authored labels independently checked through AI DOM/pixel review, not human-expert annotations. Actual Chrome/WebGPU runtime parity was measured separately; that does not establish reliable completion detection on independently developed websites.