Card: add the D1A avatar
Browse files- .gitattributes +1 -0
- README.md +2 -0
- d1a-avatar.png +3 -0
.gitattributes
CHANGED
|
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
d1a-avatar.png filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -9,6 +9,8 @@ datasets: [JohnP1/d1a-ja-jglue, JohnP1/d1a-routing]
|
|
| 9 |
tags: [d1a, decision-model, calibration, lora, gemma4, typesafe, system-one, pull-requests, on-device]
|
| 10 |
---
|
| 11 |
|
|
|
|
|
|
|
| 12 |
# D1A-E2B v0.6
|
| 13 |
|
| 14 |
D1A is a small open decision model. One document and a set of typed questions go in (yes/no, choice, score), and a calibrated probability for every option comes out, in one forward pass, with no generated text. It speaks the TypeSafe System One API (`POST /v1/systemone`), so the TypeSafe SDK and existing clients work against it.
|
|
|
|
| 9 |
tags: [d1a, decision-model, calibration, lora, gemma4, typesafe, system-one, pull-requests, on-device]
|
| 10 |
---
|
| 11 |
|
| 12 |
+
<p align="center"><img src="https://huggingface.co/JohnP1/d1a-e2b/resolve/main/d1a-avatar.png" width="200" alt="D1A avatar: an anime girl with silver-white hair and round glasses on a round #D1A badge"></p>
|
| 13 |
+
|
| 14 |
# D1A-E2B v0.6
|
| 15 |
|
| 16 |
D1A is a small open decision model. One document and a set of typed questions go in (yes/no, choice, score), and a calibrated probability for every option comes out, in one forward pass, with no generated text. It speaks the TypeSafe System One API (`POST /v1/systemone`), so the TypeSafe SDK and existing clients work against it.
|
d1a-avatar.png
ADDED
|
Git LFS Details
|