Downloads · 30 days
0
ajaxdavis/alpha-yi-f7-base-20260809
alpha-yi-f7-base-20260809 is a machine learning model from ajaxdavis. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for other. The card lists the license as other.
Do not use this revision as a semantic model or as a training parent. A post-publication audit proved that every initial F7 stage rebuilt a new BPE tokenizer while inheriting weights whose embedding and output rows we…
Downloads · 30 days
0
Access
Public
Updated Aug 10, 2026
Repo size
773 MB
Likes
0
Public
Click a slice to open those files.
.alph759 MB · 97%
From the Hugging Face model README
Do not use this revision as a semantic model or as a training parent. A post-publication audit proved that every initial F7 stage rebuilt a new BPE tokenizer while inheriting weights whose embedding and output rows were indexed by the preceding tokenizer. The checkpoint is retained only as reproducible negative evidence.
The originally published checkpoint has SHA-256
7b24eb73442400856d4306c611e834e0fdab61e713f57ff9a5d6f88e8f80b699.
Its embedded tokenizer has order-independent token-mapping SHA-256
eb8a5347f5a88cdca2ce26ca1f5748dfd2180f952ccdba374e7d1c948bca6651,
whereas the last valid parent checkpoint used token-mapping SHA-256
25c0085f847e5304ddfc3e031f747ecd1d2b291f284ff559724bdb80d0f7ca08.
This changed token IDs beneath inherited parameters and invalidates the
semantic lineage even though the run was numerically finite and its held-out
loss decreased.
The immutable original Hub revision remains available for provenance:
b4b75f28b47b9b75d4d50e6a631c0a745cea6c55. The complete original training
artifact repository is also retained as negative evidence, not as an admitted
model.
A corrected foundation line is being trained from the last valid parent with the parent tokenizer explicitly supplied, hash-locked, and verified inside every produced checkpoint. A corrected base release will replace this warning only after independent validation and sample review.
This repository makes no chat-quality, knowledge-quality, or deployment claim for the invalidated checkpoint.