Safetensors
mistral
h-j-han's picture
Create README.md
1b581ab verified
|
raw
history blame
3.04 kB
metadata
license: mit
datasets:
  - allenai/MADLAD-400
language:
  - en
  - ko
  - el
  - ru
  - bg
base_model:
  - mistralai/Mistral-7B-v0.1

VocADT is a solution for vocabulary adaptation using adapter modules that are trained to learn the optimal linear combination of existing embeddings while keeping the model’s weights fixed. VocADT offers a flexible and scalable solution without requiring external resources or language constraints.

New Vocabulary Adapted Models

Only the input/output embeddings are replaced, while all other original weights of base model remain fixed. These are the merged version: after training the adapters, we merge the original embeddings with the adapter to generate the new embeddings.

Name Adapted Model Base Model New Vocab Size Focused Languages
VocADT-Latin h-j-han/Mistral-7B-VocADT-50k-Latin Mistral 50k Swahili (sw), Indonesian (id), Estonian (et), Haitian Creole (ht), English (en)
VocADT-Mixed h-j-han/Mistral-7B-VocADT-50k-Mixed Mistral 50k Korean (ko), Greek (el), Russian (ru), Bulgarian (bg), English (en)
VocADT-Cyrillic h-j-han/Mistral-7B-VocADT-50k-Cyrillic Mistral 50k Russian (ru), Bulgarian (bg), Ukrainian (uk), Kazakh (kk), English (en)

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

# model_name = "mistralai/Mistral-7B-v0.1 # Base Model
model_name = "h-j-han/Mistral-7B-VocADT-50k-Mixed" # Vocabulary Adapted Model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

prefix = "\nEnglish: Hello \nKorean: μ•ˆλ…•ν•˜μ„Έμš” \nEnglish: Thank you\nKorean: κ³ λ§™μŠ΅λ‹ˆλ‹€\nEnglish: "
line = "I lived in Korea for seven years"
suffix = f"\nKorean:"
prompt = prefix + line + suffix

inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=10)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

# Base Model Output: "ν•œκ΅­μ— 7λ…„ μ‚΄" # This short incomplete phrase in Korean is 10 tokens for the base model.
# VocADT Output: "μ €λŠ” ν•œκ΅­μ— 7λ…„ λ™μ•ˆ μ‚΄μ•˜μŠ΅λ‹ˆλ‹€." # Complete and good output within 10 tokens

Reference

We provide code in Github repo : https://github.com/h-j-han/VocADT
Also, please find details in this paper :

@misc{han2024vocadt,
      title={Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?}, 
      author={HyoJung Han and Akiko Eriguchi and Haoran Xu and Hieu Hoang and Marine Carpuat and Huda Khayrallah},
      year={2024},
      eprint={2410.09644},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2410.09644}, 
}