deepseek-ai / deepseek-ai/DeepSeek-OCR

Failed in Colab using transformers: ImportError: cannot import name 'LlamaFlashAttention2' from 'transformers.models.llama.modeling_llama'

Open
#7 4 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
23.9k
Forks
2.2k
PR merge metrics
No merged PRs in 30d

Description

transformers: 4.57.1
torch: 2.8.0+cu126
Error messages:
`ImportError: cannot import name 'LlamaFlashAttention2' from 'transformers.models.llama.modeling_llama' (/usr/local/lib/python3.12/dist-packages/transformers/models/llama/modeling_llama.py)
`
Similar issue was found in [https://github.com/deepseek-ai/DeepSeek-VL2/issues/87](https://github.com/deepseek-ai/DeepSeek-VL2/issues/87).
Please fix it.

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.