fr

app.py

@@ -61,8 +61,8 @@ def model_inference(
       text = f"{assistant_prefix} {text}"
 
 
-    prompt = processor.apply_chat_template(resulting_messages, add_generation_prompt=True)
-    inputs = processor(text=prompt, images=[images], return_tensors="pt")
+    prompt = id_processor.apply_chat_template(resulting_messages, add_generation_prompt=True)
+    inputs = id_processor(text=prompt, images=[images], return_tensors="pt")
     inputs = {k: v.to("cuda") for k, v in inputs.items()}
 
     generation_args = {
@@ -86,9 +86,9 @@ def model_inference(
     generation_args.update(inputs)
 
     # Generate
-    generated_ids = model.generate(**generation_args)
+    generated_ids = id_model.generate(**generation_args)
 
-    generated_texts = processor.batch_decode(generated_ids[:, generation_args["input_ids"].size(1):], skip_special_tokens=True)
+    generated_texts = id_processor.batch_decode(generated_ids[:, generation_args["input_ids"].size(1):], skip_special_tokens=True)
     return generated_texts[0]
 
 # Load model