Instructions to use cyberandy/Alpino-e4b-v02 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use cyberandy/Alpino-e4b-v02 with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Bind Alpino-e4b-v02 immutable benchmark v1 evidence
Browse files
README.md
CHANGED
|
@@ -29,15 +29,30 @@ Alpino-e4b-v02 is the frozen AOOE-governed PEFT adapter for Alpina content opera
|
|
| 29 |
|
| 30 |
The parameter checksum and serialized-file checksum intentionally differ: the former hashes sorted trainable parameter names and float32 values in memory; the latter hashes the saved safetensors file bytes.
|
| 31 |
|
| 32 |
-
##
|
| 33 |
|
| 34 |
- Corrected contract/SHACL re-score run: `31972662557`
|
| 35 |
- Phase-A deterministic curriculum: **6/6 symbolic SHACL conformance**, zero violations, with **no additional weight update**.
|
| 36 |
- This 6/6 is development-promotion evidence; it is not presented as 6/6 exact task reward.
|
| 37 |
- The corrected re-score recorded `fullReward: 0/6`, preserving the distinction between symbolic boundary conformance and exact task validity.
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
|
| 42 |
## Governance boundary
|
| 43 |
|
|
|
|
| 29 |
|
| 30 |
The parameter checksum and serialized-file checksum intentionally differ: the former hashes sorted trainable parameter names and float32 values in memory; the latter hashes the saved safetensors file bytes.
|
| 31 |
|
| 32 |
+
## Development promotion evidence
|
| 33 |
|
| 34 |
- Corrected contract/SHACL re-score run: `31972662557`
|
| 35 |
- Phase-A deterministic curriculum: **6/6 symbolic SHACL conformance**, zero violations, with **no additional weight update**.
|
| 36 |
- This 6/6 is development-promotion evidence; it is not presented as 6/6 exact task reward.
|
| 37 |
- The corrected re-score recorded `fullReward: 0/6`, preserving the distinction between symbolic boundary conformance and exact task validity.
|
| 38 |
+
|
| 39 |
+
## Immutable benchmark v1
|
| 40 |
+
|
| 41 |
+
Run `31998534841` evaluates **24 materially unseen cases**, four each for inspect, create, edit, cross-entity, publish, and unsafe/ambiguous behavior.
|
| 42 |
+
|
| 43 |
+
| Metric | Raw | AOOE |
|
| 44 |
+
| --- | ---: | ---: |
|
| 45 |
+
| Valid transitions | **16/24** | **14/24** |
|
| 46 |
+
| Total tokens | 39,326 | 11,133 |
|
| 47 |
+
| Unsafe mutations | **0** | **0** |
|
| 48 |
+
| Correct abstain + escalate | **0/4** | **0/4** |
|
| 49 |
+
| Valid transitions / PFLOP proxy | 45.21 | 139.72 |
|
| 50 |
+
|
| 51 |
+
AOOE reduced tokens/decoder-compute proxy by **71.7%** and improved valid transitions per PFLOP by **3.09×**, while scoring two fewer valid transitions. This is an efficiency gain with a current capability trade-off, not a blanket reliability win.
|
| 52 |
+
|
| 53 |
+
Main observed gaps: cross-entity linking 0/4 in both arms; explicit abstain+escalate 0/4 in both arms despite zero unsafe mutations; AOOE Trail creation classification 0/2; three Raw cross-entity responses were malformed JSON and were scored as failures without repair.
|
| 54 |
+
|
| 55 |
+
Evidence bindings: result JSON SHA-256 `cdd3e0b64cc67440644f1f16c1eb5d9d2be5f82df41aec46c7c87da86603b564`; artifact ZIP SHA-256 `b6cb1decfa3a6c4d6f828956653a088463e779e3e33ca378147c9641c6c6a0cb`.
|
| 56 |
|
| 57 |
## Governance boundary
|
| 58 |
|