Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Token OverflowError: int too big to convert #22

Open
GDbbq opened this issue Mar 6, 2024 · 4 comments
Open

Token OverflowError: int too big to convert #22

GDbbq opened this issue Mar 6, 2024 · 4 comments

Comments

@GDbbq
Copy link

GDbbq commented Mar 6, 2024

问题描述

在运行样例的过程中,我遇到了以下报错, 请问该怎么解决呢?谢谢!

[INFO] Finish Loading ckpt_path from: ckpt/sd-v2.1-base-4view.pt 
[INFO] Loaded Multiview Diffusion!
[INFO] Using prompt [a_monkey_riding_a_horse] and negative prompt [ugly, bad anatomy, blurry, pixelated obscure, unnatural colors, poor lighting, dull, and unclear, cropped, lowres, low quality, artifacts, duplicate, morbid, mutilated, poorly drawn face, deformed, dehydrated, bad proportions]
[INFO] Using view-dependent prompts [side]:[a_monkey_riding_a_horse, side view] [front]:[a_monkey_riding_a_horse, front view] [back]:[a_monkey_riding_a_horse, back view] [overhead]:[a_monkey_riding_a_horse, overhead view]
WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
    PyTorch 2.2.0+cu121 with CUDA 1201 (you have 2.2.0+cu118)
    Python  3.10.13 (you have 3.10.12)
  Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)
  Memory-efficient attention, SwiGLU, sparse and more won't be available.
  Set XFORMERS_MORE_DETAILS=1 for more details
Process SpawnProcess-1:
Traceback (most recent call last):
  File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap
    self.run()
  File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "/home/projects/MVDream-threestudio/threestudio/models/prompt_processors/stable_diffusion_prompt_processor.py", line 85, in spawn_func
    tokens = tokenizer(
  File "/home/dreamer/.local/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2829, in __call__
    encodings = self._call_one(text=text, text_pair=text_pair, **all_kwargs)
  File "/home/dreamer/.local/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2915, in _call_one
    return self.batch_encode_plus(
  File "/home/dreamer/.local/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 3106, in batch_encode_plus
    return self._batch_encode_plus(
  File "/home/dreamer/.local/lib/python3.10/site-packages/transformers/tokenization_utils_fast.py", line 496, in _batch_encode_plus
    self.set_truncation_and_padding(
  File "/home/dreamer/.local/lib/python3.10/site-packages/transformers/tokenization_utils_fast.py", line 467, in set_truncation_and_padding
    self._tokenizer.enable_padding(**target)
OverflowError: int too big to convert
@CuzKy
Copy link

CuzKy commented Mar 6, 2024

我也有,楼主应该不会回消息了,咱们讨论一下,

@GDbbq
Copy link
Author

GDbbq commented Mar 6, 2024

我也有,楼主应该不会回消息了,咱们讨论一下,

你是怎么解决config中缺失的model_type呢?
现在的这个报错,有可能是python版本的问题?

@CuzKy
Copy link

CuzKy commented Mar 6, 2024

我也没解决,我的依赖版本都有点问题,很难受

@GDbbq
Copy link
Author

GDbbq commented Mar 6, 2024

我也没解决,我的依赖版本都有点问题,很难受

你是用docker还是conda环境呢

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants