Ines-1 RC1 (private staging; release commit a421eb5): no pipeline_tag; apodex-mini provenance sentence
Browse files- CHANGELOG_CLAIMS.md +1 -0
- README.md +0 -1
- SHA256SUMS +4 -4
- config.json +1 -1
- training/TRANSLATION_PROVENANCE.md +1 -1
CHANGELOG_CLAIMS.md
CHANGED
|
@@ -26,3 +26,4 @@ Each is kept here with what replaced it and how it was found.
|
|
| 26 |
| 19 | Dockerfile "not built" | Built from scratch and smoke-tested (CPU, GPU bf16: 0 of 400 answers changed vs canonical) | ENVIRONMENT.md |
|
| 27 |
| 20 | `examples/quickstart.py` and `scripts/serve_jev.py` work from any copy | They failed when run from a `snapshot_download` cache (files are symlinks to blobs and `Path.resolve()` left the snapshot); fixed with `Path.absolute()`, found by the smoke test from the private Hub repo | smoke from the Hub |
|
| 28 |
| 21 | Model weights licence pending review | Model weights, config and tokenizer: **Apache-2.0** (LICENSE, NOTICE), decided 2026-10-02; code MIT; training data keeps its own terms | LICENSING_NOTES.md §2 |
|
|
|
|
|
|
| 26 |
| 19 | Dockerfile "not built" | Built from scratch and smoke-tested (CPU, GPU bf16: 0 of 400 answers changed vs canonical) | ENVIRONMENT.md |
|
| 27 |
| 20 | `examples/quickstart.py` and `scripts/serve_jev.py` work from any copy | They failed when run from a `snapshot_download` cache (files are symlinks to blobs and `Path.resolve()` left the snapshot); fixed with `Path.absolute()`, found by the smoke test from the private Hub repo | smoke from the Hub |
|
| 28 |
| 21 | Model weights licence pending review | Model weights, config and tokenizer: **Apache-2.0** (LICENSE, NOTICE), decided 2026-10-02; code MIT; training data keeps its own terms | LICENSING_NOTES.md §2 |
|
| 29 |
+
| 22 | `pipeline_tag: text-classification` | No `pipeline_tag`: on the private staging repo the Hub attached a generic text-classification widget that no inference provider can run with this custom interface; descriptive tags kept | Hub metadata of the private repo |
|
README.md
CHANGED
|
@@ -3,7 +3,6 @@ license: apache-2.0
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
- es
|
| 6 |
-
pipeline_tag: text-classification
|
| 7 |
tags:
|
| 8 |
- mixture-of-experts
|
| 9 |
- decision-model
|
|
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
- es
|
|
|
|
| 6 |
tags:
|
| 7 |
- mixture-of-experts
|
| 8 |
- decision-model
|
SHA256SUMS
CHANGED
|
@@ -1,17 +1,17 @@
|
|
| 1 |
97ad8982da911d928c3423f164a38f80608b98289ac4f4b3f292d90ae0ef2262 .dockerignore
|
| 2 |
344fc5bfdbc9c68d218d648034f4a1651ca5bf71e513dedac9b45a8847830913 .gitattributes
|
| 3 |
862263fa1f46c20f0d1e4dac5ffcc75abd55c08211b2c3864c5f8764b9d87793 .gitignore
|
| 4 |
-
|
| 5 |
e4a1aeafc1f6c01f8fff69aef8a2518631428f3ec96db4a9a56d7bb296cce95f Dockerfile
|
| 6 |
5e98ea3d3045927158b597521fcf127ac5569e656e4e665f0c94a35e2a191980 ENVIRONMENT.md
|
| 7 |
cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30 LICENSE
|
| 8 |
6a7ddcad077839a44697c005ea7e6f455caecaa8054412913108d6e21a1c9dbe LICENSE-CODE
|
| 9 |
2d6f4e21f766eedbfe2a92b3b8058493ad4e907f5f0756049ac1e2c53e3cfd01 LICENSING_NOTES.md
|
| 10 |
178f429d8400d3f9df9e3b9cac9e64e3cff29cf9cd21bb135c91ede2866cbfe1 NOTICE
|
| 11 |
-
|
| 12 |
6ec8a2bb55f9331d77b9adbeae7fd71eeb5614a988cd21eee18c7bde775df5ba TASKSOURCE_LICENSE_AUDIT.md
|
| 13 |
058dc5687ddb161d4dbfcf1703ae059e78698714b4ce2ddf1783262c10b95142 THIRD_PARTY_DATA_NOTICE.md
|
| 14 |
-
|
| 15 |
da9bad7608ad2fd759e0e9088fd55a60a22d11ea6b8cb720040594a2b0fc556f eval/fullcase_report.json
|
| 16 |
60e288cf88dfdf189fa7582daaad8a274911ce47db6cf47f3dfe0367760fa353 eval/fullcase_report.md
|
| 17 |
a8e81da13d548c4dac0d26ecab081c4640429f1493eb607015bbca8008000d29 eval/items/v3-engram_off__tasksource.jsonl
|
|
@@ -73,7 +73,7 @@ d6c695d3cd37cde9907c505876c8c6f105fed46b60e94c2d908a9725d95f8ed9 requirements.t
|
|
| 73 |
64566a481519aaa6c543672e7e6fe7096f56fac7e4f38ea501201e02ff34a915 tasksource_license_audit.csv
|
| 74 |
859e5c63f13924ebed8dd9a3dd6690438fd084771728c1da3a220017a5e74469 tokenizer/tokenizer.json
|
| 75 |
6bb112f88cf6761e60be73f4ea2d112aa33df6dd5daf8f5b8646e91bb7397da3 tokenizer/tokenizer_identity.json
|
| 76 |
-
|
| 77 |
6440a6e61e4ae6761b32ef165beb5f7f3806c3df24e35e60c3d6ab659b8f070c training/code/audit_data.py
|
| 78 |
90d07f574c1b27b20fcbfa4e4929d2ccd2d80e680640b333837aff49a9411d24 training/code/audit_report.py
|
| 79 |
c924991b591ea6e96ce50fb5f89f92af3ad7ce5136fcfeeaad07d254b8cf1c20 training/code/decisions.py
|
|
|
|
| 1 |
97ad8982da911d928c3423f164a38f80608b98289ac4f4b3f292d90ae0ef2262 .dockerignore
|
| 2 |
344fc5bfdbc9c68d218d648034f4a1651ca5bf71e513dedac9b45a8847830913 .gitattributes
|
| 3 |
862263fa1f46c20f0d1e4dac5ffcc75abd55c08211b2c3864c5f8764b9d87793 .gitignore
|
| 4 |
+
109741891311a91409d58472eb4daa6d198e1912a8111ad5482d9991bc78c06a CHANGELOG_CLAIMS.md
|
| 5 |
e4a1aeafc1f6c01f8fff69aef8a2518631428f3ec96db4a9a56d7bb296cce95f Dockerfile
|
| 6 |
5e98ea3d3045927158b597521fcf127ac5569e656e4e665f0c94a35e2a191980 ENVIRONMENT.md
|
| 7 |
cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30 LICENSE
|
| 8 |
6a7ddcad077839a44697c005ea7e6f455caecaa8054412913108d6e21a1c9dbe LICENSE-CODE
|
| 9 |
2d6f4e21f766eedbfe2a92b3b8058493ad4e907f5f0756049ac1e2c53e3cfd01 LICENSING_NOTES.md
|
| 10 |
178f429d8400d3f9df9e3b9cac9e64e3cff29cf9cd21bb135c91ede2866cbfe1 NOTICE
|
| 11 |
+
c6d5fdace486379bf2242d2c98589f946b6cd391057ce240c77304a30742e918 README.md
|
| 12 |
6ec8a2bb55f9331d77b9adbeae7fd71eeb5614a988cd21eee18c7bde775df5ba TASKSOURCE_LICENSE_AUDIT.md
|
| 13 |
058dc5687ddb161d4dbfcf1703ae059e78698714b4ce2ddf1783262c10b95142 THIRD_PARTY_DATA_NOTICE.md
|
| 14 |
+
6935bddba3a216046ba6570cbdbd988cd285d9ee9bf4388c7ca610d2be4a6fb6 config.json
|
| 15 |
da9bad7608ad2fd759e0e9088fd55a60a22d11ea6b8cb720040594a2b0fc556f eval/fullcase_report.json
|
| 16 |
60e288cf88dfdf189fa7582daaad8a274911ce47db6cf47f3dfe0367760fa353 eval/fullcase_report.md
|
| 17 |
a8e81da13d548c4dac0d26ecab081c4640429f1493eb607015bbca8008000d29 eval/items/v3-engram_off__tasksource.jsonl
|
|
|
|
| 73 |
64566a481519aaa6c543672e7e6fe7096f56fac7e4f38ea501201e02ff34a915 tasksource_license_audit.csv
|
| 74 |
859e5c63f13924ebed8dd9a3dd6690438fd084771728c1da3a220017a5e74469 tokenizer/tokenizer.json
|
| 75 |
6bb112f88cf6761e60be73f4ea2d112aa33df6dd5daf8f5b8646e91bb7397da3 tokenizer/tokenizer_identity.json
|
| 76 |
+
dc8e89f55b7df1201cc58e3c8f1189951ed3b97f45a89cbb2e0b24ff66c99c46 training/TRANSLATION_PROVENANCE.md
|
| 77 |
6440a6e61e4ae6761b32ef165beb5f7f3806c3df24e35e60c3d6ab659b8f070c training/code/audit_data.py
|
| 78 |
90d07f574c1b27b20fcbfa4e4929d2ccd2d80e680640b333837aff49a9411d24 training/code/audit_report.py
|
| 79 |
c924991b591ea6e96ce50fb5f89f92af3ad7ce5136fcfeeaad07d254b8cf1c20 training/code/decisions.py
|
config.json
CHANGED
|
@@ -95,7 +95,7 @@
|
|
| 95 |
"engram_backend_identity": "token_id:65536:65536:197f7a314b356f70",
|
| 96 |
"training_code_commit": "0b5e63e3da05c1a51eb9f0ea1758f8d53d200a80-dirty",
|
| 97 |
"bundle_model_code_commit": "5d1ad97",
|
| 98 |
-
"bundle_release_code_commit": "
|
| 99 |
"torch_version_at_training": "2.14.0+cu130"
|
| 100 |
}
|
| 101 |
}
|
|
|
|
| 95 |
"engram_backend_identity": "token_id:65536:65536:197f7a314b356f70",
|
| 96 |
"training_code_commit": "0b5e63e3da05c1a51eb9f0ea1758f8d53d200a80-dirty",
|
| 97 |
"bundle_model_code_commit": "5d1ad97",
|
| 98 |
+
"bundle_release_code_commit": "a421eb5",
|
| 99 |
"torch_version_at_training": "2.14.0+cu130"
|
| 100 |
}
|
| 101 |
}
|
training/TRANSLATION_PROVENANCE.md
CHANGED
|
@@ -6,7 +6,7 @@ so that the historical run is documented exactly; it does not claim that a rerun
|
|
| 6 |
|
| 7 |
| | historical value |
|
| 8 |
|---|---|
|
| 9 |
-
| model name sent in the request (`--translator-model`) | `apodex-mini` |
|
| 10 |
| what that name is | the served-model alias (`--served-model-name`) of a self-hosted OpenAI-compatible server (SGLang 0.5.18) serving the public model [`apodex/Apodex-1.1-mini-FP8`](https://huggingface.co/apodex/Apodex-1.1-mini-FP8) (Apache-2.0 on its card; base model `apodex/Apodex-1.1-mini`). The alias is not a public model ID; the endpoint was a private server and is not published. The model revision served on that day was not pinned (head of the model repo checked on 2026-10-02: `709359cb`). |
|
| 11 |
| request | chat completions; `temperature` 0.3, `max_tokens` 4000, `chat_template_kwargs.enable_thinking` false; prompt in `prepare_public.py` (`translate_case`) |
|
| 12 |
| check | a translation is kept only if keys, option ids, numbers, booleans and structure are identical to the English case (3 tries, else dropped) |
|
|
|
|
| 6 |
|
| 7 |
| | historical value |
|
| 8 |
|---|---|
|
| 9 |
+
| model name sent in the request (`--translator-model`) | `apodex-mini` — **apodex-mini was the historical served-model alias used for the public apodex/Apodex-1.1-mini-FP8 model.** |
|
| 10 |
| what that name is | the served-model alias (`--served-model-name`) of a self-hosted OpenAI-compatible server (SGLang 0.5.18) serving the public model [`apodex/Apodex-1.1-mini-FP8`](https://huggingface.co/apodex/Apodex-1.1-mini-FP8) (Apache-2.0 on its card; base model `apodex/Apodex-1.1-mini`). The alias is not a public model ID; the endpoint was a private server and is not published. The model revision served on that day was not pinned (head of the model repo checked on 2026-10-02: `709359cb`). |
|
| 11 |
| request | chat completions; `temperature` 0.3, `max_tokens` 4000, `chat_template_kwargs.enable_thinking` false; prompt in `prepare_public.py` (`translate_case`) |
|
| 12 |
| check | a translation is kept only if keys, option ids, numbers, booleans and structure are identical to the English case (3 tries, else dropped) |
|