Bochkov / demo_bvv_zh

demo_bvv_zh

This repository contains the model and associated resources from the papers

📚 Paper (Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations) -

📚 Paper (Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate) -

💻 Code

Model summary

demo_bvv_zh is a conceptual bilingual (English + Chinese) transformer language model trained from scratch on a limited-size 9B-token corpus, as a demonstration of the frozen-embedding hypothesis for robust, language-agnostic and easily-combinable language models.

• Embedding matrix is frozen after visual-based (Unicode-morpheme) initialization.

• All transformer layers and output head are trainable .

• Trained on small English+Chinese dataset.

• Vocabulary: 131072 (Unicode/visual + frequent n-grams).

• 16-layer transformer, 1024 hidden dim, 32 heads.

• Demonstrates that frozen, compositional, language-agnostic embeddings allow for stable representation learning and can be directly combined into Mixture-of-Experts (MoE) models.

• Direct comparison to "unfrozen" version Bochkov/demo_bvv_unfrozen_zh .

Intended use

• Academic and engineering demonstration.
• Proof-of-concept for multilingual/fusion/frozen-embedding research.
• NOT intended or suitable for actual production generation or factual knowledge (corpus ~9B tokens only).

Model comparison (vs unfrozen baseline)

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model = AutoModelForCausalLM.from_pretrained('Bochkov/demo_bvv_zh', trust_remote_code=True).to('cuda')
tokenizer = AutoTokenizer.from_pretrained('Bochkov/demo_bvv_zh')
inputs = tokenizer("Hello! ", return_tensors="pt").to('cuda')
outputs = model.generate(
    **inputs, 
    max_new_tokens=100, 
    temperature=0.8, 
    top_k=50, 
    top_p=0.95, 
    do_sample=True
)
print(tokenizer.decode(outputs[0]))

Citation

If you find this work helpful or inspiring, please consider citing the associated papers:

@article{
      bochkov2025emergent,
      title={Emergent Semantics Beyond Token Embeddings: Transformer {LM}s with Frozen Visual Unicode Representations},
      author={Andrey Bochkov},
      journal={Transactions on Machine Learning Research},
      issn={2835-8856},
      year={2025},
      url={https://openreview.net/forum?id=Odh8IynO1o},
      note={}
}

@misc{bochkov2025growingtransformersmodularcomposition,
      title={Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate}, 
      author={A. Bochkov},
      year={2025},
      eprint={2507.07129},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2507.07129}, 
}