docs: corrected model card (recipe, host, eval caveats, DOI)

README.md

@@ -1,36 +1,76 @@
-# micro-kiki-stack-chat-fr
+---
+license: apache-2.0
+base_model: Qwen/Qwen3.5-35B-A3B
+base_model_relation: adapter
+library_name: mlx
+pipeline_tag: text-generation
+language:
+  - fr
+  - en
+tags:
+  - lora
+  - mlx
+  - qwen3.5
+  - moe
+  - chat-fr
+  - micro-kiki
+  - hypneum-lab
+  - historical
+---
 
-## 🇪🇺 EU AI Act transparency
+# micro-kiki stack-chat-fr (MLX adapter, French chat)
 
-This artefact is published under the AI Act framework (Regulation EU 2024/1689).
+Single MLX adapter file (`adapters.safetensors`, 6.76 GB) plus its iteration-1300
+checkpoint (`0001300_adapters.safetensors`, same size). Published 2026-05-05 as a
+"multi-adapter stack for French chat" on top of `Qwen/Qwen3.5-35B-A3B`.
 
-| Field | Value |
-|---|---|
-| Provider | L'Électron Rare (clemsail) |
-| Role under AI Act | GPAI provider |
-| Adapter type | MLX merged adapter — multi-adapter stack for French chat |
-| Base model | `Qwen/Qwen3.5-35B-A3B (via micro-kiki v3 LoRA stack)` |
-| License | Apache-2.0 |
-| Intended use | Multilingual French/English assistant with engineering and reasoning bias |
-| Out of scope | Healthcare diagnosis, legal advice, autonomous safety-critical decisions |
-| Risk classification | Limited risk — Article 50 transparency obligations apply |
-| Copyright respect | Training data does not include scraped copyrighted material |
-| Full provenance | https://github.com/L-electron-Rare/eu-kiki/tree/main/docs/provenance |
-| Contact | postmaster@saillant.cc |
-
-⚠️ **You are using an AI model.** Outputs may be inaccurate, biased or
-fabricated. Do not act on them without independent verification, especially
-in regulated domains.
-
-
-## Benchmarks (HumanEval+ n=164)
-
-| Metric | Value |
+> **Provenance warning.** No `adapter_config.json`, no training log and no eval of this
+> exact file are shipped. Base model, rank, target layers, learning rate and data are
+> therefore **not recorded** for this artefact; the base model in the frontmatter is the
+> one declared by the original card and could not be verified from files. Prefer
+> `micro-kiki-v4-sota/chat-fr` (fully documented) for any use.
+
+## Recipe
+
+| Parameter | Value |
 |---|---|
-| n_problems | 164 |
-| max_tokens | 384 |
-| pass@1 | 0.5426829268292683 |
-| total_gen_s | 729.7 |
+| Base model (declared) | `Qwen/Qwen3.5-35B-A3B` |
+| Framework | MLX (`mlx_lm`), BF16 |
+| Iterations | ≥ 1300 (from the checkpoint file name) |
+| Rank / scale / layers / lr / seq length | not recorded |
+| Training data | micro-kiki `chat-fr` domain (French instruction/chat corpus, incl. Opus-distilled samples); counts not recorded |
+
+## Training host & cost
+
+Mac Studio M3 Ultra 512 GB, MLX BF16 (project default). Peak memory, wall-clock, energy:
+not recorded. Host powered off since 2026-10.
+
+## Evaluation
+
+The file `evals/chat-fr-164-cross.json` kept in this repository reports HumanEval+
+(n=164, max_tokens 384) **pass@1 = 0.543**, total generation 729.7 s — but its own
+metadata says it was run with `base_model = Qwen3.6-35B-A3B` and
+`adapter = lora-qwen36-35b-v4-sota/chat-fr`, i.e. on the **V4-SOTA chat-fr adapter, not
+on this file**. No evaluation of this 6.76 GB adapter is recorded.
+
+June 2026 iact-bench caveat: on Qwen3.6-35B-A3B, the sibling ailiance LoRA family showed
+no gain over the base except `html-css`; no comparable measurement exists for this adapter.
+
+## Limitations
+
+Undocumented recipe; research artefact; no safety tuning; not for medical, legal or
+financial advice.
+
+## Citation
+
+micro-kiki concept DOI **10.5281/zenodo.19666759**.
+
+## Provenance
+
+<https://github.com/hypneum-lab/micro-kiki> · <https://github.com/ailiance/ailiance-mac-tuner>
 
-Raw JSON committed under `evals/`.
+## EU AI Act transparency
 
+LoRA adapter weights only, base unchanged; provider Clément Saillant / L'Electron Rare for
+Hypneum Lab; limited risk, Article 50; contact clement@saillant.cc. Outputs may be
+inaccurate, biased or fabricated.