hongxingli
/

SpatialLadder-3B

Image-Text-to-Text

Model card Files Files and versions

hongxingli commited on Oct 9, 2025

Commit

32dc991

·

verified ·

1 Parent(s): d4e53d8

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -43,7 +43,7 @@ from qwen_vl_utils import process_vision_info
 # We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
 model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
-     "inclusionAI/GUI-G2-7B",
      torch_dtype=torch.bfloat16,
      attn_implementation="flash_attention_2",
      device_map="auto")

 # We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
 model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+     "hongxingli/SpatialLadder-3B",
      torch_dtype=torch.bfloat16,
      attn_implementation="flash_attention_2",
      device_map="auto")