wehub-resource-sync
e06fe8e8c6
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Waiting to run
New model PR merged notification / Notify new model (push) Waiting to run
Update Transformers metadata / build_and_package (push) Waiting to run
Secret Leaks / trufflehog (push) Failing after 1s
Build documentation / build (push) Failing after 1s
Build documentation / build_other_lang (push) Failing after 0s
CodeQL Security Analysis / CodeQL Analysis (push) Failing after 0s
PR CI / pr-ci (push) Failing after 1s
Slow tests on important models (on Push - A10) / Get all modified files (push) Failing after 1s
Slow tests on important models (on Push - A10) / Model CI (push) Has been skipped
17 lines
441 B
Python
17 lines
441 B
Python
from transformers.modeling_utils import AttentionInterface
|
|
from transformers.models.llama.modeling_llama import LlamaAttention
|
|
|
|
|
|
def custom_flex(x, **kwargs):
|
|
"""Dummy function."""
|
|
return x
|
|
|
|
|
|
ALL_ATTENTION_FUNCTIONS = AttentionInterface()
|
|
# This indexing statement and associated function should be exported correctly!
|
|
ALL_ATTENTION_FUNCTIONS["flex_attention"] = custom_flex
|
|
|
|
|
|
class GlobalIndexingAttention(LlamaAttention):
|
|
pass
|