Add/Update generated README.md

README.md

@@ -24,7 +24,7 @@ https://github.com/ashimdahal/captioning_image/blob/main
 
 **⚠️ Important:** The `base_model` tag in the metadata above is initially empty. The models listed here are *heuristic guesses* based on the training directory name (`microsoft-git-base_microsoft-git-base`). Please verify these against your training configuration and update the `base_model:` list in the YAML metadata block at the top of this README with the correct Hugging Face model identifiers.
 
-## How to Use (Example with PEFT)
+## How to Use (Example with PEFT)::: This is generated by script and not verified manually so proceed with caution
 
 ```python
 from transformers import AutoProcessor, AutoModelForVision2Seq, Blip2ForConditionalGeneration # Or other relevant classes
@@ -34,41 +34,41 @@ import torch
 # --- Configuration ---
 # 1. Specify the EXACT base model identifiers used during training
 # base_processor_id = "microsoft/git-base" # <-- Replace with correct HF ID
-# base_model_id = "microsoft/git-base" # <-- Replace with correct HF ID (e.g., Salesforce/blip2-opt-2.7b)
+base_model_id = "microsoft/git-base" # <-- Replace with correct HF ID (e.g., Salesforce/blip2-opt-2.7b)
 
 # 2. Specify the PEFT adapter repository ID (this repo)
-# adapter_repo_id = "ashimdahal/microsoft-git-base_microsoft-git-base"
+adapter_repo_id = "ashimdahal/microsoft-git-base_microsoft-git-base"
 
 # --- Load Base Model and Processor ---
-# processor = AutoProcessor.from_pretrained(base_processor_id)
+processor = AutoProcessor.from_pretrained(base_processor_id)
 
 # Load the base model (ensure it matches the type used for training)
 # Example for BLIP-2 OPT:
-# base_model = Blip2ForConditionalGeneration.from_pretrained(
-#     base_model_id,
-#     torch_dtype=torch.float16 # Or torch.bfloat16 or float32, match training/inference needs
-# )
+base_model = Blip2ForConditionalGeneration.from_pretrained(
+     base_model_id,
+     torch_dtype=torch.float16 # Or torch.bfloat16 or float32, match training/inference needs
+ )
 # Or for other model types:
-# base_model = AutoModelForVision2Seq.from_pretrained(base_model_id, torch_dtype=torch.float16)
+base_model = AutoModelForVision2Seq.from_pretrained(base_model_id, torch_dtype=torch.float16)
 
 # --- Load PEFT Adapter ---
 # Load the adapter config and merge the adapter weights into the base model
-# model = PeftModel.from_pretrained(base_model, adapter_repo_id)
-# model = model.merge_and_unload() # Merge weights for inference (optional but often recommended)
-# model.eval() # Set model to evaluation mode
+model = PeftModel.from_pretrained(base_model, adapter_repo_id)
+model = model.merge_and_unload() # Merge weights for inference (optional but often recommended)
+model.eval() # Set model to evaluation mode
 
 # --- Inference Example ---
-# device = "cuda" if torch.cuda.is_available() else "cpu"
-# model.to(device)
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model.to(device)
 #
-# image = ... # Load your image (e.g., using PIL)
-# text = "a photo of" # Optional prompt start
+image = ... # Load your image (e.g., using PIL)
+text = "a photo of" # Optional prompt start
 #
-# inputs = processor(images=image, text=text, return_tensors="pt").to(device, torch.float16) # Match model dtype
-#
-# generated_ids = model.generate(**inputs, max_new_tokens=50)
-# generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0].strip()
-# print(f"Generated Caption: {{generated_text}}")
+inputs = processor(images=image, text=text, return_tensors="pt").to(device, torch.float16) # Match model dtype
+
+generated_ids = model.generate(**inputs, max_new_tokens=50)
+generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0].strip()
+print(f"Generated Caption: {{generated_text}}")
 
 ```