Vchitect
/

ShotVL-3B

Image-Text-to-Text

vision-language

text-generation-inference

Model card Files Files and versions

Alexislhb commited on Jun 27

Commit

e1120f0

·

verified ·

1 Parent(s): c4de598

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -81,13 +81,13 @@ dtype = torch.bfloat16
 video_path = "/path/to/video.mp4"
 model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
-  "Vchitect/ShotVL-7B",
   device_map=device_map,
   attn_implementation="flash_attention_2",
   torch_dtype=dtype,
 ).eval()
 processor = AutoProcessor.from_pretrained(
-  "Vchitect/ShotVL-7B", revision="refs/pr/24", use_fast=True, torch_dtype=dtype
 )
 question = (

 video_path = "/path/to/video.mp4"
 model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+  "Vchitect/ShotVL-3B",
   device_map=device_map,
   attn_implementation="flash_attention_2",
   torch_dtype=dtype,
 ).eval()
 processor = AutoProcessor.from_pretrained(
+  "Vchitect/ShotVL-3B", revision="refs/pr/24", use_fast=True, torch_dtype=dtype
 )
 question = (