AttributeError: 'LlamaModel' object has no attribute '_use_flash_attention_2'

I was running speedup.sh with Llama model but got this issue trace.

The error follows from the file Consistency_LLM/cllm/cllm_llama_modeling.py

Consistency_LLM/cllm/cllm_llama_modeling.py

Line 154 in b2a7283

if self.model._use_flash_attention_2:

the code needs to be updated to
if self.model.config._attn_implementation=='flash_attention_2':
Do i need to change model config to check speed of base model with jacobi iteration?
base model="meta-llama/Meta-Llama-3-8B-Instruct"

Did you use package versions we provided in requirements.txt? If not, what are the pytorch and transformers versions you are using?

With all respect, the versions in requirements.txt are quite dated (transformers 4.36).
could you please make an effort and find a solution that works with the current transformers version.

Also, please reduce the requirements.txt size from 180 packages to some manageable minimum, and avoid locking to specific version unless critical.