423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-29 18:20:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

imporve log

Browse Source 
Former-commit-id: a6abf375975ffea3d51e1b944c9855b5f62ffac8
This commit is contained in:
hiyouga
2025-01-08 09:56:10 +00:00
parent da931e73c8
commit 760dea0787
16 changed files with 78 additions and 67 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llamafactory/model/model_utils/longlora.py
View File

@@ -31,10 +31,10 @@ from transformers.models.llama.modeling_llama import (
apply_rotary_pos_emb,
repeat_kv,
)
from transformers.utils.versions import require_version
from ...extras import logging
from ...extras.constants import SUPPORTED_CLASS_FOR_S2ATTN
from ...extras.misc import check_version
from ...extras.packages import is_transformers_version_greater_than
@@ -353,7 +353,7 @@ def llama_sdpa_attention_forward(
def _apply_llama_patch() -> None:
require_version("transformers>=4.41.2,<=4.46.1", "To fix: pip install transformers>=4.41.2,<=4.46.1")
check_version("transformers>=4.41.2,<=4.46.1")
LlamaAttention.forward = llama_attention_forward
LlamaFlashAttention2.forward = llama_flash_attention_2_forward
LlamaSdpaAttention.forward = llama_sdpa_attention_forward