|
--- |
|
license: openrail |
|
datasets: |
|
- cc100 |
|
language: |
|
- ja |
|
pipeline_tag: text-generation |
|
--- |
|
# AIBunCho/japanese-novel-gpt-j-6b |
|
|
|
[AI BunCho](https://bun-cho.work/)で利用しているモデルです。2021年に作った小説用言語モデルです。 |
|
|
|
## Model Details |
|
|
|
GPT-J-6BをTPUで2週間日本語tokenizerを用いて日本語データで事前学習し、その後2週間小説データで転移学習したものです。 |
|
|
|
|
|
## Uses |
|
|
|
Google colabのT4 High-RAMで動作確認しています。 |
|
|
|
``` |
|
pip install transformers sentencepiece accelerate |
|
``` |
|
|
|
|
|
```python |
|
from transformers import GPTJForCausalLM, AlbertTokenizer |
|
import torch |
|
|
|
tokenizer = AlbertTokenizer.from_pretrained('AIBunCho/japanese-novel-gpt-j-6b', keep_accents=True, remove_space=False) |
|
|
|
model = GPTJForCausalLM.from_pretrained("AIBunCho/japanese-novel-gpt-j-6b", torch_dtype=torch.float16, low_cpu_mem_usage=True) |
|
|
|
model.half() |
|
model.eval() |
|
|
|
if torch.cuda.is_available(): |
|
model = model.to("cuda") |
|
|
|
prompt = """ |
|
わたくしといふ現象は |
|
""".strip() |
|
|
|
input_ids = tokenizer.encode( |
|
prompt, |
|
add_special_tokens=False, |
|
return_tensors="pt" |
|
).cuda() |
|
|
|
# this is for reproducibility. |
|
# feel free to change to get different result |
|
seed = 27 |
|
torch.manual_seed(seed) |
|
|
|
tokens = model.generate( |
|
input_ids.to(device=model.device), |
|
max_new_tokens=32, |
|
temperature=0.6, |
|
top_p=0.9, |
|
repetition_penalty=1.2, |
|
do_sample=True, |
|
pad_token_id=tokenizer.pad_token_id, |
|
bos_token_id=tokenizer.bos_token_id, |
|
eos_token_id=tokenizer.eos_token_id |
|
) |
|
|
|
out = tokenizer.decode(tokens[0], skip_special_tokens=True) |
|
print(out) |
|
"""わたくしといふ現象は、その因果律を断ち切ることができるのです。""" |
|
|
|
``` |
|
|
|
[More Information Needed] |
|
|
|
## Bias, Risks, and Limitations |
|
|
|
The pre-training dataset may have contained offensive or inappropriate content even after applying data cleansing filters which can be reflected in the model generated text. We recommend users exercise reasonable caution when using these models in production systems. Do not use the model for any applications that may cause harm or distress to individuals or groups. |
|
|
|
### Training Data |
|
|
|
cc100の日本語データ |
|
|
|
Wikipedia |
|
|
|
その他webデータ |
|
|
|
## Author |
|
|
|
X(旧Twitter): [@OsoneHiroyuki](https://twitter.com/OsoneHiroyuki) |
|
|
|
## Acknowledgements |
|
|
|
[Google TPU research cloud](https://sites.research.google/trc/about/)の支援を受けて学習を行いました。 |
|
|
|
|
