GLM4-9b- chat模型加载踩坑

最新推荐文章于 2026-05-06 10:20:43 发布

原创最新推荐文章于 2026-05-06 10:20:43 发布 · 306 阅读

0 ·

本内容遵循CC 4.0 BY-SA版权协议

标签

#深度学习 #pytorch #python

1.在官网上下载了，ChatGLM4的模型文件和运行代码

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
import os

os.environ[
    'CUDA_VISIBLE_DEVICES'] = '0'  # Set the GPU number. If inference with multiple GPUs, set multiple GPU numbers
MODEL_PATH = "THUDM/glm-4-9b-chat-hf"

device = "cuda" if torch.cuda.is_available() else "cpu"

tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH, trust_remote_code=True)

query = "你好"

inputs = tokenizer.apply_chat_template([{"role": "user", "content": query}],
                                       add_generation_prompt=True,
                                       tokenize=True,
                                       return_tensors="pt",
                                       return_dict=True
                                       )

inputs = inputs.to(device)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_PATH,
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    trust_remote_code=True,
    device_map="auto"
).eval()

gen_kwargs = {"max_length": 2500, "do_sample": True, "top_k": 1}
with torch.no_grad():
    outputs = model.generate(**inputs, **gen_kwargs)
    outputs = outputs[:, inputs['input_ids'].shape[1]:]
    print(tokenizer.decode(outputs[0], skip_special_tokens=True))

出现报错：raise HFValidationError( huggingface_hub.errors.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '../LLM/glm-4-9b-chat'. Use repo_type argument if needed.

搜了资料说是路径有问题，不知道为甚麽MODEL_PATH不支持用相对路径了，只支持用绝对路径了。

2.改为绝对路径之后，报错

AttributeError: ‘ChatGLMForConditionalGeneration’ object has no attribute ‘_extract_past_from_model_output’

解决方案，将transformers升级或降级到4.46.0，再运行模型（完美解决）。

pip install transformers==4.46.0