rinna
/
japanese-gpt-1b
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
Tianyu Zhao 2023-03-22 04:09:05 +00:00 committed by huggingface-web
parent 44d3fdefa7
commit e50d65b5a2
1 changed files with 3 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -25,13 +25,11 @@ This repository provides a 1.3B-parameter Japanese GPT model. The model was trai
# How to use the model # How to use the model
*NOTE:* Use `T5Tokenizer` to initiate the tokenizer.
~~~~ ~~~~
import torch import torch
from transformers import T5Tokenizer, AutoModelForCausalLM from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = T5Tokenizer.from_pretrained("rinna/japanese-gpt-1b") tokenizer = AutoTokenizer.from_pretrained("rinna/japanese-gpt-1b", use_fast=False)
model = AutoModelForCausalLM.from_pretrained("rinna/japanese-gpt-1b") model = AutoModelForCausalLM.from_pretrained("rinna/japanese-gpt-1b")
if torch.cuda.is_available(): if torch.cuda.is_available():
@ -51,7 +49,7 @@ with torch.no_grad():
pad_token_id=tokenizer.pad_token_id, pad_token_id=tokenizer.pad_token_id,
bos_token_id=tokenizer.bos_token_id, bos_token_id=tokenizer.bos_token_id,
eos_token_id=tokenizer.eos_token_id, eos_token_id=tokenizer.eos_token_id,
bad_word_ids=[[tokenizer.unk_token_id]] bad_words_ids=[[tokenizer.unk_token_id]]
) )
output = tokenizer.decode(output_ids.tolist()[0]) output = tokenizer.decode(output_ids.tolist()[0])