faysalbenahmed/AMF-v0.18-Qualified-Realization

AMF v0.18 — Qualified Hybrid Intelligence Realization

From general-purpose models to qualified intelligence realizations.

Mission + Constraints
        |
        v
       AMF
        |
        v
Qualified Intelligence Realization
    or qualified refusal

AMF treats models as raw material, capabilities as qualified components, and AI systems as architectures engineered for a mission.

This repository publishes a complete AMF realization qualified under a bounded internal protocol, together with a standard PEFT representation of its neural component.

Verdict: QUALIFIED_INTELLIGENCE_REALIZATION under the AMF internal qualification protocol
Selected realization: g02-reuse-g01-canonicalize-historical-be
Mission: explicit_evidence_sufficiency_v5_cumulative_scientist

Measured results

Evaluation	Parent	AMF v0.18	Gain
ROB	71.88%	90.63%	+18.75 pts
OOD	50.00%	85.16%	+35.16 pts
Fresh Final	47.66%	81.25%	+33.59 pts

Schema validity remained at 100% across all three evaluations.

These results describe a bounded mission and its supported representation families. They are not a claim of universal reliability or external certification.

Release integrity

Verification	Result
PEFT configuration resolution	PASS
PEFT type	LoRA
Task type	CAUSAL_LM
Portable and qualified adapter weights	Byte-identical
Modification of the qualified adapter	0
Modification of historical evidence	0
Base-model revision	Pinned

The portable adapter resolves to:

Base model
mistralai/Mistral-7B-Instruct-v0.3

Pinned revision
c170c708c41dac9275d15a8fff4eca08d52bab71

Why this matters

Most AI delivery pipelines stop at a model checkpoint.

AMF addresses a broader question:

Can this exact realization be identified, reproduced, constrained and evaluated for a declared mission?

The delivered object is not only a set of weights. It is an evidence-carrying realization with explicit lineage, pinned dependencies, operating contracts, qualification boundaries and a reproducible execution context.

For R&D teams, this establishes a clear separation between experimentation, qualification and publication.

For organizations deploying AI, it creates a traceable path from:

"We tested a model."

to:

"We know what was built,
from which components,
under which constraints,
and what was actually qualified."

Portable by design. Qualified through evidence.

The repository root provides a standard Hugging Face PEFT interface:

adapter_config.json
adapter_model.safetensors

The portable adapter weights are byte-identical to the historical qualified artifact.

Portability does not redefine the qualification claim. The complete realization also includes its canonicalization layer, execution runtime, input/output contract and qualification evidence.

This separation provides standard interoperability without rewriting experimental history.

Portable PEFT component

For Hugging Face and PEFT compatibility, the repository root exposes:

adapter_model.safetensors  byte-identical copy of the qualified adapter weights
adapter_config.json        portable configuration pointing to the pinned base model

These convenience files represent only the neural adapter component. Loading the root-level PEFT adapter alone does not reproduce the complete qualified realization. The qualified object also requires CANONICALIZE_TO_RECORDS_V1, the evidence-sufficiency contract and the AMF runtime described below.

The historical files in qualified_adapter_exact/ remain unchanged. The relationship between the historical and portable files is recorded in PORTABLE_ADAPTER_RECEIPT.json and PORTABLE_ADAPTER_MANIFEST.sha256.

from transformers import AutoModelForCausalLM
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained(
    "mistralai/Mistral-7B-Instruct-v0.3",
    revision="c170c708c41dac9275d15a8fff4eca08d52bab71",
    device_map="auto",
)
model = PeftModel.from_pretrained(
    base,
    "faysalbenahmed/AMF-v0.18-Qualified-Realization",
)

Use runtime/inference.py for the complete public realization.

Exact realization identity

• Base model: mistralai/Mistral-7B-Instruct-v0.3
• Pinned revision: c170c708c41dac9275d15a8fff4eca08d52bab71
• Adapter tree SHA-256 (AMF tree identity): 36c1f91df36aa00802ea65d721657b5a1af699f23b0beaddf9d95e3afd741145
• Adapter weights SHA-256: 88094b7f6a88586eb5201efa7051f10232602c618d3eb8e34046f18bb16dcb71
• Adapter size: 6,839,183 bytes (tree total recorded by AMF)
• Input transform: CANONICALIZE_TO_RECORDS_V1
• Canonicalizer source SHA-256: 5f32ab909812fa239233be764cfdc6286ea33197314108c2670c8b5ef5f03af3
• Qualified identity receipt: 5ed5db3b97bc011a19a66243f1accbc89db1c4afc1da4925c7c29317ff5c553e
• Qualification verdict receipt: 8949f3af288ee1ffa16a01e04f66467f7726414c26a9af5a3d84d9e569bb552e

qualified_adapter_exact/ contains the adapter files exactly as present in the qualified lineage. The original adapter_config.json intentionally retains its historical local cache path; the convenience runtime loads the pinned base model explicitly and then attaches the adapter.

Reproducibility / provenance

• Source mission package SHA-256: 3571f1f7b934e9e8cd5cafd2b021e96765a4adbe576c1072a5605f395c9aa030
• Canonical result archive SHA-256: de60ddb8b5dfc4061aa285c132d89b6fdbd168b508f81d419af1ce358c435493
• Ledger events: 92
• Ledger head SHA-256: 054311b729e4ab8b0d8d53cf74ae76a9ce5262dab80fdd0efc87898d2344d819
• Run state: SUCCEEDED
• Integrity state: VALID
• Qualification Authority verdict: QUALIFIED_INTELLIGENCE_REALIZATION

Machine-readable provenance is in AMF_EVIDENCE.json. Qualification contracts and exact public evidence receipts are included without disclosing protected rows.

The original RUN_RESULT.json contains publication_ready=false because the campaign's built-in gated Hugging Face exporter was not executed during the run. The qualification verdict itself is independent of that publication workflow and is preserved unchanged in evidence/QUALIFICATION_VERDICT.json.

Public Evidence Projections

The repository also publishes three reproducible views of selected scientific experiments from the frozen v0.18 campaign:

• v018-exp-001 — representation canonicalization — SUPPORTED
• v018-exp-002 — LoRA continuation / neural mutation — SUPPORTED
• v018-exp-003 — raw substrate switch — REFUTED

These artifacts expose bounded claims, source references, observable lineage, evidence bindings, adjudication state and derived integrity checks without replacing the canonical Scientific Event Ledger or exposing the Foundry's private experiment-selection machinery.

See public-evidence/ for the three JSON projections and the AMF Public Evidence Projection Contract v0.1.

The projections were validated for deterministic rebuild, traceability, targeted fail-closed tamper rejection and byte-identical regeneration.

They do not alter the terminal QUALIFIED_INTELLIGENCE_REALIZATION verdict published by this repository.

Quick start

Install dependencies:

pip install -r runtime/requirements.txt

Run the convenience inference helper:

python runtime/inference.py examples/example_input.json

The base model is fetched from the pinned Hugging Face revision. A GPU suitable for Mistral 7B is expected for this convenience runner.

Important: runtime/inference.py is a post-campaign convenience helper. The qualification evidence is bound to the original AMF evaluation runtime recorded by the campaign; this helper is not itself the qualification authority.

Repository layout

qualified_adapter_exact/   exact qualified lineage adapter
canonicalizer/             exact CANONICALIZE_TO_RECORDS_V1 source
runtime/                   public inference helper + exact prompt/parser source
contracts/                 mission, qualification and operation contracts
evidence/                  aggregate receipts and qualification/freeze records
public-evidence/           reproducible scientific experiment projections
examples/                  synthetic public example
release/                   portable public bundle ZIP
AMF_EVIDENCE.json          machine-readable public provenance
MANIFEST.sha256            SHA-256 of every published file

Evidence structure

• evidence/ contains the sanitized terminal qualification receipts for the published qualified realization.
• public-evidence/ contains deterministic public projections of selected experiments from the canonical scientific archive.
• AMF_EVIDENCE.json provides the machine-readable publication-level provenance summary and index.

Experimental support does not confer terminal qualification authority.

In short:

public-evidence/  -> how selected transformations were experimentally evaluated
evidence/         -> why the terminal realization received qualification authority

Experimental evidence and terminal qualification evidence are related, but they are not interchangeable.

What is intentionally not published

This repository does not contain protected dataset rows, Fresh Final rows, protected/Fresh Final seeds, protected/final prediction files, or the raw 170 MB result archive. Those remain private so the original evidence is not casually exposed or reused as if it were fresh protected evidence in future campaigns.

Scope and limitations

• QUALIFIED_INTELLIGENCE_REALIZATION is an AMF protocol verdict, not an external third-party certification.
• The release demonstrates bounded performance on this mission and its supported representation families; it does not imply universal reliability.
• The hashes establish integrity and lineage. They do not, by themselves, prove the correctness of every scientific design choice.
• The realization still uses Mistral 7B; this is not yet a demonstration of edge deployment or micro-model inference.
• No GDPR/RGPD compliance claim is made by this release.

Attribution

AMF — AI Mission Foundry
Created and developed by Fayçal Benahmed
Stack Moderne — France
Independent research and engineering project
https://stack-moderne.fr/

License / third-party components

This realization is designed for use with mistralai/Mistral-7B-Instruct-v0.3, pinned to revision:

c170c708c41dac9275d15a8fff4eca08d52bab71

The Mistral base-model weights are not included in this repository and remain governed by their upstream Apache 2.0 license and applicable notices.

The AMF adapter, canonicalizer, contracts, runtime and evidence materials remain governed by the terms specified by the repository owner. This public release is currently marked license: other; no additional rights should be inferred beyond those explicitly granted.

Third-party software and components remain governed by their respective licenses.

Français — résumé

v0.18 démontre qu'AMF peut explorer plusieurs loci d'intervention, sélectionner une réalisation hybride admissible, la figer avant l'évaluation protégée, puis atteindre un verdict terminal QUALIFIED_INTELLIGENCE_REALIZATION. La publication reste volontairement assainie : les lignes protégées, le Fresh Final brut et leurs seeds ne sont pas exposés.