reader-lm：小模型 html转markdown

loong_XL2024-09-13 8:50

参考：

https://huggingface.co/jinaai/reader-lm-0.5b

在线demo：

https://colab.research.google.com/drive/1wXWyj5hOxEHY6WeHbOwEzYAC0WB1I5uA#scrollTo=0mG9ISzHOuKK

输入网址：https://www.galaxy-geely.com/E5

结果：

代码：

c 复制代码

# pip install transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "jinaai/reader-lm-0.5b"

device = "cuda" # for GPU usage or "cpu" for CPU usage
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)

# example html content
html_content = "<html><body><h1>Hello, world!</h1></body></html>"

messages = [{"role": "user", "content": html_content}]
input_text=tokenizer.apply_chat_template(messages, tokenize=False)

print(input_text)

inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
outputs = model.generate(inputs, max_new_tokens=1024, temperature=0, do_sample=False, repetition_penalty=1.08)

print(tokenizer.decode(outputs[0]))