docs: note candidate-mode order sensitivity
Browse files
README.md
CHANGED
|
@@ -22,7 +22,7 @@ Tancho studies how a drone could decide what to observe next after a flood or ea
|
|
| 22 |
Training and evaluation sources differ by release. They include procedural synthetic scenes and limited public disaster UAV imagery; each model card states the source, measured results, corrections, and remaining limits.
|
| 23 |
|
| 24 |
- **[Tancho Observation Program v8](https://huggingface.co/v13s/tancho)** — A Cosmos3-Edge derivative for Reasoner and Generator roles. The model names unanswered questions and proposes semantic observation requirements. The repository root holds the v8 weights. Its 104/104 exact final result is from synthetic scenes, not an independent real-image benchmark.
|
| 25 |
-
- **[Tancho Cosmos Decision Preview](https://huggingface.co/v13s/tancho/tree/main/decision-preview)** — Experimental Jev-style candidate selection weights in the same repository. On one Modal L4, median decision-stage time on 12 real flood scenes, each tested in two candidate orders, was 0.5033 s versus 40.4724 s for v8 JSON generation (80.4x). This primarily measures the change from sequential generation to a single forward pass for candidate scoring, not a gain from training the new weights. Agreement with AI-review labels was 11/24 versus 12/24 for v8 using the same candidate mode; the preview has not shown an accuracy gain.
|
| 26 |
- **[Tancho Generator v5](https://huggingface.co/v13s/tancho-generator-v5)** — A historical research baseline for numeric viewpoint generation, with different weights and output contracts from v8.
|
| 27 |
|
| 28 |
Tancho model weights are distributed under OpenMDW 1.1. Read the linked model cards for benchmark scope and license details.
|
|
|
|
| 22 |
Training and evaluation sources differ by release. They include procedural synthetic scenes and limited public disaster UAV imagery; each model card states the source, measured results, corrections, and remaining limits.
|
| 23 |
|
| 24 |
- **[Tancho Observation Program v8](https://huggingface.co/v13s/tancho)** — A Cosmos3-Edge derivative for Reasoner and Generator roles. The model names unanswered questions and proposes semantic observation requirements. The repository root holds the v8 weights. Its 104/104 exact final result is from synthetic scenes, not an independent real-image benchmark.
|
| 25 |
+
- **[Tancho Cosmos Decision Preview](https://huggingface.co/v13s/tancho/tree/main/decision-preview)** — Experimental Jev-style candidate selection weights in the same repository. On one Modal L4, median decision-stage time on 12 real flood scenes, each tested in two candidate orders, was 0.5033 s versus 40.4724 s for v8 JSON generation (80.4x). This primarily measures the change from sequential generation to a single forward pass for candidate scoring, not a gain from training the new weights. Agreement with AI-review labels was 11/24 versus 12/24 for v8 using the same candidate mode; the preview has not shown an accuracy gain, and single-order choices in this candidate mode depend strongly on option position.
|
| 26 |
- **[Tancho Generator v5](https://huggingface.co/v13s/tancho-generator-v5)** — A historical research baseline for numeric viewpoint generation, with different weights and output contracts from v8.
|
| 27 |
|
| 28 |
Tancho model weights are distributed under OpenMDW 1.1. Read the linked model cards for benchmark scope and license details.
|