423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-04 04:32:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix flashattn warning

Browse Source 
Former-commit-id: 4bd8e3906d09bf6ec4b8f6b553a347fca9db4f80
This commit is contained in:
hiyouga 2023-11-10 18:34:54 +08:00
parent 55e097aaac
commit 982e0e79c2
2 changed files with 10 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/llmtuner/extras/patches/llama_patch.py
View File

@ -5,11 +5,14 @@ from typing import Optional, Tuple
from transformers.utils import logging
from transformers.models.llama.modeling_llama import LlamaAttention, apply_rotary_pos_emb, repeat_kv
is_flash_attn_2_available = False
try:
from flash_attn import flash_attn_func, flash_attn_varlen_func # type: ignore
from flash_attn.bert_padding import pad_input, unpad_input # type: ignore
is_flash_attn_2_available = True
except ImportError:
print("FlashAttention-2 is not installed, ignore this if you are not using FlashAttention.")
is_flash_attn_2_available = False
logger = logging.get_logger(__name__)

3
src/llmtuner/tuner/core/loader.py
View File

@ -123,9 +123,12 @@ def load_model_and_tokenizer(
# Set FlashAttention-2
if model_args.flash_attn:
if getattr(config, "model_type", None) == "llama":
if LlamaPatches.is_flash_attn_2_available:
LlamaModule.LlamaAttention = LlamaPatches.LlamaFlashAttention2
LlamaModule.LlamaModel._prepare_decoder_attention_mask = LlamaPatches._prepare_decoder_attention_mask
logger.info("Using FlashAttention-2 for faster training and inference.")
else:
logger.warning("FlashAttention-2 is not installed.")
elif getattr(config, "model_type", None) in ["qwen", "Yi"]:
logger.info("Current model automatically enables FlashAttention if installed.")
else: