thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png
datasets:
- mc4
- wikipedia
- EleutherAI/pile
- oscar-corpus/colossal-oscar-1.0
- cc100
language:
- ja
- en
tags:
- qwen
inference: false
rinna/nekomata-14b
Overview
We conduct continual pre-training of qwen-14b on 66B tokens from a mixture of Japanese and English datasets. The continual pre-training significantly improves the model's performance on Japanese tasks. It also enjoys the following great features provided by the original Qwen model.
- The inclusive Qwen vocabulary (vocab size > 150k) enables the model to processs Japanese texts much more efficiently than the previously released youri series.
- The model supports a maximum sequence length of 8192.
The name nekomata comes from the Japanese word 猫又/ねこまた/Nekomata, which is a kind of Japanese mythical creature (妖怪/ようかい/Youkai).
Library
The model was trained using code based on aws-neuron/neuronx-nemo-megatron.
Model architecture
A 40-layer, 5120-hidden-size transformer-based language model. Please refer to the Qwen paper for architecture details.
Continual pre-training
The model was initialized with the qwen-14b model and continually trained on around 66B tokens from a mixture of the following corpora
- Japanese CC-100
- Japanese C4
- Japanese OSCAR
- The Pile
- Wikipedia
- rinna curated Japanese dataset
Training Infrastructure
nekomata-14Bwas trained on 16 nodes of Amazon EC2 trn1.32xlarge instance powered by AWS Trainium purpose-built ML accelerator chip. The pre-training job was completed within a timeframe of approximately 7 days.Authors
Benchmarking
Please refer to rinna's LM benchmark page.
How to use the model
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("rinna/nekomata-14b", trust_remote_code=True)
# Use GPU with bf16
# model = AutoModelForCausalLM.from_pretrained("rinna/nekomata-14b", device_map="auto", trust_remote_code=True, bf16=True)
# Use GPU with fp16
# model = AutoModelForCausalLM.from_pretrained("rinna/nekomata-14b", device_map="auto", trust_remote_code=True, fp16=True)
# Use CPU
# model = AutoModelForCausalLM.from_pretrained("rinna/nekomata-14b", device_map="cpu", trust_remote_code=True)
# Automatically select device and precision
model = AutoModelForCausalLM.from_pretrained("rinna/nekomata-14b", device_map="auto", trust_remote_code=True)
text = "西田幾多郎は、"
token_ids = tokenizer.encode(text, add_special_tokens=False, return_tensors="pt")
with torch.no_grad():
output_ids = model.generate(
token_ids.to(model.device),
max_new_tokens=200,
min_new_tokens=200,
do_sample=True,
temperature=1.0,
top_p=0.95,
pad_token_id=tokenizer.pad_token_id,
bos_token_id=tokenizer.bos_token_id,
eos_token_id=tokenizer.eos_token_id
)
output = tokenizer.decode(output_ids.tolist()[0])
print(output)
Tokenization
The model uses the original Qwen tokenizer. It augments the cl100k tiktoken tokenizer and has a vocabulary size of 151,936. The inclusive vocabulary helps the model to reach a better tokenization efficiency, especially for Japanese texts.
We compared the Qwen tokenizer (as used in nekomata) and the llama-2 tokenizer (as used in youri) on different text collections and found that the Qwen tokenizer achieves a much better byte2token rate (i.e. the average number of tokens produced from 1 byte of text) as following. A lower byte2token rate indicates a better tokenization efficiency.
| Tokenizer | Japanese | English | Multilingual |
|---|---|---|---|
| Qwen | 0.24 | 0.27 | 0.27 |
| llama-2 | 0.40 | 0.29 | 0.36 |
How to cite
@misc{RinnaNekomata14b,
url={https://huggingface.co/rinna/nekomata-14b},
title={rinna/nekomata-14b},
author={Zhao, Tianyu and Kaga, Akio and Sawada, Kei}
}