BhashaAI
/

ViLaH

Visual Question Answering

image-text-to-text

text-generation-inference

Model card Files Files and versions Community

damerajee commited on May 28, 2024

Commit

b51c18b

·

verified ·

1 Parent(s): 3640907

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -56,7 +56,7 @@ inputs = processor(text=text, images=test_image, return_tensors="pt").to("cuda")
 for k,v in inputs.items():
   print(k,v.shape)
-MAX_LENGTH = 500
 # Autoregressively generate
 # We use greedy decoding here, for more fancy methods see https://huggingface.co/blog/how-to-generate
 generated_ids = base_model.generate(**inputs, max_new_tokens=MAX_LENGTH)
@@ -95,7 +95,7 @@ inputs = processor(text=text, images=test_image, return_tensors="pt").to("cuda")
 for k,v in inputs.items():
   print(k,v.shape)
-MAX_LENGTH = 500
 # Autoregressively generate
 # We use greedy decoding here, for more fancy methods see https://huggingface.co/blog/how-to-generate
 generated_ids = base_model.generate(**inputs, max_new_tokens=MAX_LENGTH)

 for k,v in inputs.items():
   print(k,v.shape)
+MAX_LENGTH = 200
 # Autoregressively generate
 # We use greedy decoding here, for more fancy methods see https://huggingface.co/blog/how-to-generate
 generated_ids = base_model.generate(**inputs, max_new_tokens=MAX_LENGTH)
 for k,v in inputs.items():
   print(k,v.shape)
+MAX_LENGTH = 200
 # Autoregressively generate
 # We use greedy decoding here, for more fancy methods see https://huggingface.co/blog/how-to-generate
 generated_ids = base_model.generate(**inputs, max_new_tokens=MAX_LENGTH)