license: apache-2.0
language:
- en
- ja
programming_language:
- C
- C++
- C#
- Go
- Java
- JavaScript
- Lua
- PHP
- Python
- Ruby
- Rust
- Scala
- TypeScript
library_name: transformers
pipeline_tag: text-generation
inference: false
llm-jp-13b-v2.0
This repository provides large language models developed by LLM-jp, a collaborative project launched in Japan.
| Pre-trained models |
| llm-jp-13b-v2.0 |
Checkpoints format: Hugging Face Transformers
Required Libraries and Their Versions
- torch>=2.2.2
- transformers>=4.39.3
- tokenizers>=0.15.2
- accelerate>=0.27.2
- flash-attn>=2.5.6
Usage
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("llm-jp/llm-jp-13b-v2.0")
model = AutoModelForCausalLM.from_pretrained("llm-jp/llm-jp-13b-v2.0", device_map="auto", torch_dtype=torch.float16)
text = "自然言語処理とは何か"
tokenized_input = tokenizer.encode(text, add_special_tokens=False, return_tensors="pt").to(model.device)
with torch.no_grad():
output = model.generate(
tokenized_input,
max_new_tokens=100,
do_sample=True,
top_p=0.95,
temperature=0.7,
repetition_penalty=1.05,
)[0]
print(tokenizer.decode(output))
Model Details
- Model type: Transformer-based Language Model
- Total seen tokens: 256B
| Model | Params | Layers | Hidden size | Heads | Context length |
|---|---|---|---|---|---|
| 13b model | 13b | 40 | 5120 | 40 | 4096 |
Training
Pre-training:
- Hardware: 128 A100 40GB GPUs (mdx cluster)
- Software: Megatron-LM
Instruction tuning:
- Hardware: 8 A100 40GB GPUs (mdx cluster)
- Software: TRL, PEFT, and DeepSpeed
Tokenizer
The tokenizer of this model is based on huggingface/tokenizers Unigram byte-fallback model.
The vocabulary entries were converted from llm-jp-tokenizer v2.2 (50k).
Please refer to README.md of llm-ja-tokenizer for details on the vocabulary construction procedure (the pure SentencePiece training does not reproduce our vocabulary).
- Model: Hugging Face Fast Tokenizer using Unigram byte-fallback model which requires
tokenizers>=0.14.0 - Training algorithm: Marging Code/English/Japanese vocabularies constructed with SentencePiece Unigram byte-fallback and reestimating scores with the EM-algorithm.
- Training data: A subset of the datasets for model pre-training
- Vocabulary size: 96,867 (mixed vocabulary of Japanese, English, and source code)
- The acutal size of vocabulary in the pretrained model is 97,024 due to round-up to multiples of 256.
Datasets
Pre-training
The models have been pre-trained using a blend of the following datasets.
| Language | Dataset | Tokens |
|---|---|---|
| Japanese | Wikipedia | 1.4B |
| Common Crawl | 130.7B | |
| English | Wikipedia | 4.7B |
| The Pile | 110.3B | |
| Codes | The Stack | 8.7B |
Instruction tuning (To be updated)
The models have been fine-tuned on the following datasets.
| Language | Dataset | description |
|---|---|---|
| Japanese | jaster | An automatically transformed data from the existing Japanese NLP datasets |
| databricks-dolly-15k | A translated one by DeepL in LLM-jp | |
| OpenAssistant Conversations Dataset | A translated one by DeepL in LLM-jp |
Evaluation
You can view the evaluation results of several LLMs on this leaderboard. We used llm-jp-eval (v1.3.0) for the evaluation.
Risks and Limitations
The models released here are still in the early stages of our research and development and have not been tuned to ensure outputs align with human intent and safety considerations.
Send Questions to
llm-jp(at)nii.ac.jp
License
Model Card Authors (To be updated)
The names are listed in alphabetical order.
Namgi Han, Tatsuya Hiraoka, Hirokazu Kiyomaru, Takashi Kodama, and Hiroshi Matsuda.