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

feat: support loading gemma2 as vlm text model

Browse Source
This commit is contained in:
drbh 2024-12-06 10:46:49 -05:00
parent 5df8059037
commit 0f0fe9a998
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
server/text_generation_server/models/custom_modeling/vlm.py
View File

@ -17,6 +17,12 @@ def load_text_model(prefix, config, weights, name=None):
)
return FlashGemmaForCausalLM(prefix, config, weights, causal=False)
elif config.model_type == "gemma2":
from text_generation_server.models.custom_modeling.flash_gemma2_modeling import (
FlashGemma2ForCausalLM,
)
return FlashGemma2ForCausalLM(prefix, config, weights)
elif config.model_type == "paligemma":
from text_generation_server.models.custom_modeling.flash_gemma_modeling import (
FlashGemmaForCausalLM,