Upload folder using huggingface_hub

README.md

@@ -1,5 +1,5 @@
 ---
-library_name: mimirai
+library_name: mimir
 license: other
 license_name: mythologic-community-license
 license_link: LICENSE
@@ -63,15 +63,15 @@ tool calls, verifying claims.
 
 ## Installation
 
-The `mimirai` package is launched and is the way to use this model:
+The `mimir` package is launched and is the way to use this model:
 
 ```bash
-pip install "mimirai[local]"      # CPU engine
-pip install "mimirai[local-gpu]"  # CUDA engine
-pip install mimirai               # data models and HTTP client only
+pip install "mimir[local]"      # CPU engine
+pip install "mimir[local-gpu]"  # CUDA engine
+pip install mimir               # data models and HTTP client only
 ```
 
-Python 3.11 or later. `mimirai` is the package, `mimir` the import.
+Python 3.11 or later. The distribution and the import are both `mimir`.
 
 ## Quickstart
 
@@ -119,18 +119,18 @@ state — and `decide_many` batches many decisions while every method has an asy
 
 ## Load paths
 
-**This repo holds all three load paths.** The release root is the `mimirai` contract
+**This repo holds all three load paths.** The release root is the `mimir` contract
 (ONNX graphs plus certified policy); the same weights ship as plain `transformers` under
 a subfolder, and only what you load is downloaded:
 
 | Path | Format | Best at |
 |---|---|---|
-| **`Mythologic/MIMIR-1`** (this repo root) | ONNX graphs + certified policy via `mimirai` | routing, gating, verification |
+| **`Mythologic/MIMIR-1`** (this repo root) | ONNX graphs + certified policy via `mimir` | routing, gating, verification |
 | **`Mythologic/MIMIR-1`, `subfolder="transformers"`** | same weights for plain `transformers` | research, custom runtimes |
 
 ### Package mode (recommended)
 
-`mimirai` handles chunking, typed readouts, evidence, the distance gate and the
+`mimir` handles chunking, typed readouts, evidence, the distance gate and the
 certificate in one call, and additionally serves them over HTTP and MCP:
 
 ```bash
@@ -144,7 +144,7 @@ the full API reference are in the package repository, with a docs site.
 
 ### Transformers mode
 
-With no `mimirai` install (tested `transformers==5.17`):
+With no `mimir` install (tested `transformers==5.17`):
 
 ```python
 from transformers import AutoModel, AutoTokenizer
@@ -158,7 +158,7 @@ outputs.utilities  # [4 depths, records, candidates]: every depth's readouts
 ```
 
 Load plus forward on pre-encoded batches only: text handling, calibration, the server
-and MCP stay in `mimirai`. The staged modelling code holds the inference-only head
+and MCP stay in `mimir`. The staged modelling code holds the inference-only head
 forward — no loss, no training machinery — the same computation the shipped `model.onnx`
 already carries.
 
@@ -277,7 +277,7 @@ shipped decision must match.
 | `transformers/config.json` | encoder and head shapes, `auto_map`, architectures |
 | `transformers/modeling_mimir.py`, `transformers/configuration_mimir.py` | the architecture, `transformers` and `torch` only |
 | `tokenizer.json` | the 50,368-entry vocabulary |
-| `config.json` | variants, limits, layout and graph contract for `mimirai` |
+| `config.json` | variants, limits, layout and graph contract for `mimir` |
 | `policy/fp32.json` (+ `.npz`) | the certified selective thresholds |
 | `equivalence/` | 200 records with inputs, so any CPU replays the graph |
 | `manifest.json` | SHA-256 of every file above |
@@ -286,8 +286,8 @@ No optimiser state, no scheduler state, no RNG. Training cannot be resumed from
 
 ## Links
 
-- Package: `mimirai` on PyPI (`https://pypi.org/project/mimirai/`), `from mimir import Mimir`
-- Code: [abderahmane-ai/mimirai](https://github.com/abderahmane-ai/mimirai) on GitHub
+- Package: `mimir` on PyPI (`https://pypi.org/project/mimir/`), `from mimir import Mimir`
+- Code: [abderahmane-ai/mimir](https://github.com/abderahmane-ai/mimir) on GitHub
 
 ## Licence
 

manifest.json

@@ -1,7 +1,7 @@
 {
   "format_version": 1,
   "files": {
-    "README.md": "750154de4a18eb8fe5d6ed9477df66a54370e8bf9bb3f3ff2897018c856e1045",
+    "README.md": "3520fdf73a5c2c299b1d1d57d98996c7f84f7ac108e4163ae0a869ae807816b1",
     "config.json": "10cbc7c171d2ce17fcf214f8ba31e08a8a8f68ea422e7bb92930c719b30c1ce4",
     "equivalence/expected.npz": "8317cc5b1e8c1e7168b991fdd030ea7e1eb45fbbbbd7922a07d302876bd67118",
     "equivalence/inputs.npz": "53777dff2852935d1009f556834f0607f1a25d9775c215632a13bd544300b29c",
@@ -21,6 +21,6 @@
     "transformers/tokenizer.json": "bc2788d5ddc9e2ced5d7a6aa695b30bb0c56751e60fd65ac595b16b9f0784812"
   },
   "loadable_by": {
-    "mimirai": ">=1,<2"
+    "mimir": ">=1,<2"
   }
 }