Upload README.md with huggingface_hub

README.md

@@ -58,11 +58,14 @@ python scripts/hf_inference_emoji_demo.py --hf_repo Potpov/grimoire-checkpoints
 All three are verified working (torch 2.0.1 / cu118 / diffvg-from-source).
 
 ### Notes
-- Build the VSQ from its **own** `vsq/config.yaml` (not the ART config's `stage1_params`, which
-  under-specifies the VSQ architecture).
-- `emoji/vsq/config.yaml` was **corrected** to match the weights (`quantized_dim=512,
-  num_codes_per_shape=1, single_code_representation=true, fsq_levels=[7,5,5,5,5]`); the originally
-  saved config did not. `mnist_color/*` configs are the repo configs.
+- Build the VSQ from its **own** `vsq/config.yaml`. `mnist_color/*` configs are the repo configs.
+- `emoji/vsq` is `emoji_VSQ_hydra_small_noout` (`hydra` decoder, `single_code_representation=true`,
+  `num_segments=16`, `pred_color=true`) — the properly-trained emoji VSQ; it reconstructs emojis
+  faithfully. (An earlier push used the older `VSQ_EMOJI_COLOR`, which under-reconstructed.)
+- **Loading the ART (stage-2) checkpoints:** strip only the *leading* `model.` prefix (a blanket
+  `replace("model.","")` also deletes the inner `.model.` in `transformer.model.layers.*` → the
+  transformer loads as random weights) and remap `.ff.3.`→`.ff.2.` (x-transformers version shift).
+  `scripts/hf_generate_demo.py:_remap_key` does this. VSQ checkpoints load with a plain leading-prefix strip.
 
 ## Requirements
 torch 2.0.1 (cu118) · diffvg (from source) · see the code repo's `install.sh` / `requirements.txt`.