Update README.md

README.md

@@ -3,16 +3,15 @@ license: apache-2.0
 library_name: transformers
 pipeline_tag: feature-extraction
 ---
-
 # bvv241-max: Unified Unicode Tokenizer (SOTA Intersection) with Frozen Embeddings
 
-This model was presented in the paper [Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate](https://arxiv.org/abs/2507.07129).
+## Tokenizer Description
 
-Code: [https://github.com/Bochkov/BVV241](https://github.com/Bochkov/BVV241)
+This repository contains the tokenizer and associated resources from the papers
 
-## Tokenizer Description
+[📚 Paper (Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations)](https://huggingface.co/papers/2507.04886) - 
 
-<!-- Provide a longer summary of what this model is. -->
+[💻 Code](https://github.com/AVBochkov/Embeddings)
 
 This tokenizer is based on a hybrid vocabulary:  
 
@@ -35,23 +34,15 @@ No training or adaptation; suitable for plug-and-play use in research on embeddi
 ## How to Get Started with the Tokenizer
 
 ```python
-
 from transformers import AutoTokenizer
-
 from huggingface_hub import hf_hub_download
-
 import torch
-
 tokenizer = AutoTokenizer.from_pretrained('Bochkov/bvv241-max')
-
-
 emb_path = hf_hub_download(
     repo_id="Bochkov/bvv241-max",
     filename="normalized_embeddings_weights.pt"
 )
-
 embeddings = torch.load(emb_path)
-
 ```
 
 ## 🧑‍🔬 Citation & Concept
@@ -68,7 +59,6 @@ If you use this model or the underlying concepts in your research, please cite o
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2507.04886}, 
 }
-
 @misc{bochkov2025growingtransformersmodularcomposition,
       title={Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate}, 
       author={A. Bochkov},
@@ -80,4 +70,4 @@ If you use this model or the underlying concepts in your research, please cite o
 }
 ```
 
-This work demonstrates that transformer blocks, not token embeddings, carry the semantic burden in LLMs — a step toward modular, fusable, multilingual LMs.
+This work demonstrates that transformer blocks, not token embeddings, carry the semantic burden in LLMs — a step toward modular, fusable, multilingual LMs.