Bochkov / demo_bvv_unfrozen_zh

demo_bvv_unfrozen_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_unfrozen_zh is a 500M parameter Causal Language Model (LM) trained as an open proof-of-concept for the "frozen embeddings" paradigm. This version uses fully trainable token embeddings – a standard setup – and serves as a baseline for direct comparison with the corresponding "frozen-embedding" model Bochkov/demo_bvv_zh.

• Architecture: Transformer, rotary positional encoding
• Vocabulary: Custom Unicode-based, 131072 tokens
• Embedding: Unfrozen (trainable, classic)
• Pretraining data: 9B tokens, (Wikipedia, SQuAD2.0, TriviaQA, NQ etc) and 10% SFT (instruction/factual Q&A) mixed in
• Purpose: Compare learning capacity and generalization of full vs. frozen-embedding LMs on small data
• Trained on small English+Chinese dataset.
• Vocabulary: 131072 (Unicode/visual + frequent n-grams).
• 16-layer transformer, 1024 hidden dim, 32 heads.

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 frozen baseline)

Example Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model = AutoModelForCausalLM.from_pretrained('Bochkov/demo_bvv_unfrozen_zh', trust_remote_code=True).to('cuda')
tokenizer = AutoTokenizer.from_pretrained('Bochkov/demo_bvv_unfrozen_zh')
inputs = tokenizer("Hello, world! ", 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}, 
}