huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 12:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove scaffolding.

Browse Source
This commit is contained in:
Nicolas Patry 2024-05-07 10:20:34 +00:00
parent ddc0dd57f7
commit 649f088519
1 changed files with 0 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
server/text_generation_server/models/__init__.py
View File

@ -48,33 +48,6 @@ FLASH_ATT_ERROR_MESSAGE = "{} requires Flash Attention enabled models."
FLASH_ATTENTION = True
from text_generation_server.models.flash_rw import FlashRWSharded
from text_generation_server.models.flash_neox import FlashNeoXSharded
from text_generation_server.models.flash_llama import (
FlashLlama,
)
from text_generation_server.models.flash_qwen2 import (
FlashQwen2,
)
from text_generation_server.models.flash_cohere import (
FlashCohere,
)
from text_generation_server.models.flash_gemma import (
FlashGemma,
)
from text_generation_server.models.flash_santacoder import (
FlashSantacoderSharded,
)
from text_generation_server.models.idefics import IDEFICSSharded
from text_generation_server.models.llava_next import LlavaNext
from text_generation_server.models.idefics2 import Idefics2
from text_generation_server.models.flash_mistral import FlashMistral
from text_generation_server.models.flash_mixtral import FlashMixtral
from text_generation_server.models.flash_phi import FlashPhi
from text_generation_server.models.flash_starcoder2 import FlashStarcoder2
from text_generation_server.models.flash_dbrx import FlashDbrx
from text_generation_server.utils.flash_attn import HAS_FLASH_ATTN_V2_CUDA
try:
from text_generation_server.models.flash_rw import FlashRWSharded
from text_generation_server.models.flash_neox import FlashNeoXSharded