【大模型】Llama3-8B报错_sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg) TypeError:not a string

最新推荐文章于 2024-07-29 17:27:49 发布

原创

最新推荐文章于 2024-07-29 17:27:49 发布 · 923 阅读

2 ·

CC 4.0 BY-SA版权

文章标签：

#深度学习 #人工智能 #llama3-8B #LLM

【大模型】Llama3-8B报错_sentencepiece.SentencePieceProcessor_LoadFromFileself, arg TypeError: not a string

环境
运行模型
错误信息
- 分析错误
解决方案
- 测试
参考

环境

Ubuntu22.04
python3.11

运行模型

Llama3-8B-Chinese-Chat下载地址：

https://hf-mirror.com/shenzhi-wang/Llama3-8B-Chinese-Chat

跑 Llama3-8B-Chinese-Chat 模型：

from transformers import LlamaTokenizer, AutoModelForCausalLM

model_id = "shenzhi-wang/Llama3-8B-Chinese-Chat"

tokenizer = LlamaTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, torch_dtype="auto", device_map="auto"
)

messages = [
    {"role": "user", "content": "写一首诗吧"},
]

input_ids = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, return_tensors="pt"
).to(model.device)

outputs = model.generate(
    input_ids,
    max_new_tokens=8192,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))