Flora_7B-laser
A LaserRMT modification of ResplendentAI/Flora_7B.
LaserRMT (layer-selective rank reduction) alters the base model's existing weight matrices. It is not a format conversion and not a quantisation: the weights differ from the base in substance, not merely in numeric representation.
| Base model | ResplendentAI/Flora_7B |
| Licence | cc-by-sa-4.0, inherited from the base |
| Architecture | MistralForCausalLM, 32 layers (unchanged from the base) |
| Modification | LaserRMT layer-selective rank reduction |
Provenance and EU AI Act Art. 53 note
This card was written on 2026-08-03. The repository had carried only a single-line description since it was created on 2024-03-18 — modified weights published with no licence reasoning, no architecture record, and no statement of who provides the model. That is the gap this card closes, and it is worth stating plainly rather than quietly backfilling.
The base model above was not guessed from the repository name. It is recorded
in this repo's own config.json as _name_or_path, and the licence is the one
the base declares on the Hub as of 2026-08-03 — cc-by-sa-4.0 on both sides, so
this repository redistributes under the same terms it received.
Provider status. Most cstr/* repositories are format conversions, where
the upstream research team remains the provider of the model under Regulation
(EU) 2024/1689 and the conversion changes only the numeric representation. This
repository is not one of those. Modifying weights places a new model on the
market, so the obligations that survive the Art. 53(2) free-and-open-source
exemption — Art. 53(1)(c) and 53(1)(d) — attach here.
Art. 53(1)(c) — copyright policy. This repository does not introduce any
training corpus of its own, so no text or data mining was carried out here and
no rights reservations under Art. 4(3) of Directive (EU) 2019/790 were engaged
by this step. The modification operates on weights already published by the base
model's authors under cc-by-sa-4.0. Where the base model's own training raises
copyright questions, those attach to the base model's provider, whose
documentation is linked above. Any credible claim that this repository
redistributes material it has no right to redistribute will be acted on —
contact via the Community tab.
Art. 53(1)(d) — training content. No additional training corpus was
introduced by this repository. The model's training content is that of
ResplendentAI/Flora_7B, and
its documentation is the summary that applies. This repository does not restate
it, because restating training data documentation second-hand is how inaccurate
provenance claims propagate.
A note on the chain. ResplendentAI/Flora_7B is itself a merge — it ships a
mergekit_config.yml — so the training content that ultimately applies is that
of its constituent models rather than of a single training run. Reconstructing
that chain is the base model provider's documentation to give, not this
repository's to assert.
Known limitation. The precise LaserRMT configuration used in 2024 — which layers were reduced, and to what rank — is not recorded in this repository. It is not reconstructible from the weights alone with confidence, and it is not asserted here rather than being guessed at.