Card: pipeline and TEI warning, loader from the Hub, link to the main card

README.md

@@ -16,14 +16,18 @@ tags:
 # s1d1-router, six sources, tiny, PyTorch fp16 (safetensors)
 
 A "System 1" router: it reads a user prompt and returns its complexity score (0.01 to 1.00), its task type (19 classes)
-and whether it needs tools. It never picks a model; the deployer maps these outputs to models with rules.
+and whether it needs tools. It never picks a model; the deployer maps these outputs to models with rules. The method,
+the training data, the full results and the limitations are in the card of the main repository,
+[scombat/s1d1-router](https://huggingface.co/scombat/s1d1-router).
 
 - Variant: `v7_small_l6-fp16`, mmBERT-small cut to 6 layers, 32k vocabulary, distilled from the full model.
 - Format: PyTorch fp16 (safetensors), 85 MB.
 - Outputs: 21 logits. Output 0 is the complexity in tier units (score = 0.5 + 0.25 x output, clipped to 0.01..1.00),
-  outputs 1 to 19 are the task logits, output 20 is the needs_tools logit. Task order and decoding:
-  `release/s1d1-router/s1d1_router.py` in the project.
-- Pruned vocabulary variants ship `vocab_map.npy` (full tokenizer id -> pruned id); the project's loader applies it.
+  outputs 1 to 19 are the task logits (order in `task_names` of `config.json`), output 20 is the needs_tools logit.
+- Pruned vocabulary variants ship `vocab_map.npy` (full tokenizer id -> pruned id); the loader below applies it.
+- **Do not read it through `pipeline("text-classification")` with its defaults, nor through Text Embeddings
+  Inference**: both apply one softmax over the 21 outputs. `config.json` declares `problem_type: regression`, so
+  `pipeline(..., top_k=None)` returns the raw outputs; decode them as the main card shows.
 
 ## Measures (validation, 4,914 rows, six sources, unweighted)
 
@@ -38,13 +42,12 @@ Full results and method: `docs/15-catalog-v4-v7.md` in the project; `eval.json`
 
 ## Use
 
-```bash
-hf download scombat/s1d1-router-6src-tiny --local-dir s1d1-router-tiny
-```
+`s1d1_router.py` from [scombat/s1d1-router](https://huggingface.co/scombat/s1d1-router) loads this repository directly (Python >= 3.10,
+`tokenizers`, `huggingface_hub` and `torch`):
 
 ```python
-from s1d1_router import Router          # release/s1d1-router/s1d1_router.py in the project
-router = Router("s1d1-router-tiny")
+from s1d1_router import Router
+router = Router("scombat/s1d1-router-6src-tiny")
 router.route(["Quelle est la capitale de l'Australie ?"])
 ```
 
@@ -63,6 +66,6 @@ condition).
   title  = {s1d1-router: a one-pass multilingual router for LLM requests},
   author = {scombat},
   year   = {2026},
-  howpublished = {\url{https://huggingface.co/scombat}}
+  howpublished = {\url{https://huggingface.co/scombat/s1d1-router}}
 }
 ```