语言: 希伯来语
缩略图: https://avatars1.githubusercontent.com/u/3617152?norod.jpg
小部件:
- 文本: "远古时代"
- 文本: "十二个封印的女巫"
- 文本: "\n\n世界上最后一个人/"
- 文本: "很久很久以前"
- 文本: "赫敏藏起了"
- 文本: "突然,一道绿光"
许可证: MIT
希伯来语-GPT新-XL-诗歌
这是一个希伯来语诗歌文本生成模型,基于hebrew-gpt_neo-xl进行了微调。
数据集
汇集了各种希伯来语书籍、杂志和诗歌文集。
训练配置
类似于此配置
使用方法
Google Colab笔记本
可在此处获取这里
简单使用示例代码
!pip install tokenizers==0.10.3 transformers==4.8.0
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Norod78/hebrew-gpt_neo-xl-poetry")
model = AutoModelForCausalLM.from_pretrained("Norod78/hebrew-gpt_neo-xl-poetry", pad_token_id=tokenizer.eos_token_id)
prompt_text = "我喜欢巧克力和蛋糕"
max_len = 512
sample_output_num = 3
seed = 1000
import numpy as np
import torch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
n_gpu = 0 if torch.cuda.is_available()==False else torch.cuda.device_count()
print(f"device: {device}, n_gpu: {n_gpu}")
np.random.seed(seed)
torch.manual_seed(seed)
if n_gpu > 0:
torch.cuda.manual_seed_all(seed)
model.to(device)
encoded_prompt = tokenizer.encode(
prompt_text, add_special_tokens=False, return_tensors="pt")
encoded_prompt = encoded_prompt.to(device)
if encoded_prompt.size()[-1] == 0:
input_ids = None
else:
input_ids = encoded_prompt
print("input_ids = " + str(input_ids))
if input_ids != None:
max_len += len(encoded_prompt[0])
if max_len > 2048:
max_len = 2048
print("Updated max_len = " + str(max_len))
stop_token = "<|endoftext|>"
new_lines = "\n\n\n"
sample_outputs = model.generate(
input_ids,
do_sample=True,
max_length=max_len,
top_k=50,
top_p=0.95,
num_return_sequences=sample_output_num
)
print(100 * '-' + "\n\t\t输出\n" + 100 * '-')
for i, sample_output in enumerate(sample_outputs):
text = tokenizer.decode(sample_output, skip_special_tokens=True)
text = text[: text.find(stop_token) if stop_token else None]
text = text[: text.find(new_lines) if new_lines else None]
print("\n{}: {}".format(i, text))
print("\n" + 100 * '-')