Commit Graph
1 Commits
Author SHA1 Message Date
Alby96andClaude Opus 5.5 78e77818eb Read the tone of English headlines with the pinned ONNX model of SPEC 4.5 (refs #57)
ci / test (postgres) (push) Failing after 6m20s
ci / test (sqlite) (push) Failing after 5m59s
ci / image (push) Skipped
ci / test (postgres) (pull_request) Failing after 4m51s
ci / test (sqlite) (pull_request) Successful in 5m29s
ci / image (pull_request) Skipped
The classifier is distilroberta-finetuned-financial-news-sentiment-analysis in
Xenova's quantized ONNX export, pinned at revision e6953e30 and checked by size and
SHA-256.

- Model download: the model is not in the repository. The news job downloads it in
  the background into the models folder of the data directory, the first time, and
  retries after 6 hours if that fails. Until then the keywords judge alone, as
  SPEC 10.3 requires.
- Tokenizer: RoBERTa's byte-level BPE travels inside the DLL, read with
  BpeTokenizer and the RoBERTa pre-tokenizer. CodeGenTokenizer.Create adds ids for
  runs of spaces that the model rejects. No special tokens are recognised in
  untrusted text.
- Token check: the test compares the ids on 14 headlines with an independent copy
  of the GPT-2 encoder run on the same files.
- Model test: it reads the tone of clear headlines at 23-24 ms per title on one
  thread. It runs where the model is already downloaded and is skipped in CI.

Microsoft.ML.OnnxRuntime 1.31.1 and Microsoft.ML.Tokenizers 2.0.1 come from the
ADR 0004 list. Google.Protobuf joins the known indirect dependencies.

Anubis and Anubis.Server now declare win-x64 among their runtime identifiers, so
their lock files hold the Windows native packages. Publishing the Windows zip no
longer rewrites the lock files.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-15 12:00:54 +01:00