Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Hotfix: pass through model revision in `VlmCausalLM` (#2258)

This commit is contained in:
Daniël de Kok 2024-07-19 15:59:00 +02:00 committed by GitHub
parent 3b41e93a09
commit 3f37a66774
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
server/text_generation_server/models/vlm_causal_lm.py
View File

@ -261,7 +261,12 @@ class VlmCausalLM(FlashCausalLM):
**processor_kwargs, **processor_kwargs,
) )
self.batch_class = batch_class self.batch_class = batch_class
super().__init__(model_id=model_id, **kwargs) super().__init__(
model_id=model_id,
revision=revision,
trust_remote_code=trust_remote_code,
**kwargs,
)
@property @property
def batch_type(self) -> Type[VlmCausalLMBatch]: def batch_type(self) -> Type[VlmCausalLMBatch]: