mirror of
https://github.com/deepseek-ai/Janus.git
synced 2026-11-05 00:57:18 +00:00
[GH-ISSUE #63] 使用januspro-1B时的torch版本问题 #50
Labels
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/Janus#50
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @453251 on GitHub (Jan 28, 2025).
Original GitHub issue: https://github.com/deepseek-ai/Janus/issues/63
使用januspro-1B的时候会遇到如下报错：
return self.fget.__get__(instance, owner)() Traceback (most recent call last): File "/root/autodl-tmp/Janus/main.py", line 43, in <module> outputs = vl_gpt.language_model.generate( File "/root/miniconda3/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "/root/miniconda3/lib/python3.10/site-packages/transformers/generation/utils.py", line 2255, in generate result = self._sample( File "/root/miniconda3/lib/python3.10/site-packages/transformers/generation/utils.py", line 3254, in _sample outputs = self(**model_inputs, return_dict=True) File "/root/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/root/miniconda3/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py", line 831, in forward outputs = self.model( File "/root/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/root/miniconda3/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py", line 559, in forward causal_mask = self._update_causal_mask( File "/root/miniconda3/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py", line 661, in _update_causal_mask causal_mask = self._prepare_4d_causal_attention_mask_with_cache_position( File "/root/miniconda3/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py", line 727, in _prepare_4d_causal_attention_mask_with_cache_position causal_mask = torch.triu(causal_mask, diagonal=1) RuntimeError: "triu_tril_cuda_template" not implemented for 'BFloat16'好像是官方requirements.txt中指定的torch=2.0.1中的triu不支持BFloat16（应该是这样），将torch版本修改为torch=2.2.2后解决
@zhl102208 commented on GitHub (Jan 30, 2025):
torch版本的问题