Add/Update generated README.md

README.md

@@ -6,8 +6,9 @@ tags:
 - generated-by-script
 - peft # Assume PEFT adapter unless explicitly a full model repo
 - image-captioning # Add more specific task tags if applicable
-base_model:
-- nlpconnect/vit-gpt2-image-captioning # Heuristic guess for decoder, VERIFY MANUALLY
+base_model: [] # <-- FIXED: Provide empty list as default to satisfy validator
+# - nlpconnect/vit-gpt2-image-captioning # Heuristic guess for processor, VERIFY MANUALLY
+# - nlpconnect/vit-gpt2-image-captioning # Heuristic guess for decoder, VERIFY MANUALLY
 ---
 
 # Model: ashimdahal/nlpconnect-vit-gpt2-image-captioning_nlpconnect-vit-gpt2-image-captioning
@@ -24,7 +25,7 @@ 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 (`nlpconnect-vit-gpt2-image-captioning_nlpconnect-vit-gpt2-image-captioning`). 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)::: This is generated by script and not verified manually so proceed with caution
+## How to Use (Example with PEFT)
 
 ```python
 from transformers import AutoProcessor, AutoModelForVision2Seq, Blip2ForConditionalGeneration # Or other relevant classes
@@ -33,7 +34,7 @@ import torch
 
 # --- Configuration ---
 # 1. Specify the EXACT base model identifiers used during training
-# base_processor_id = "nlpconnect/vit-gpt2-image-captioning" # <-- Replace with correct HF ID
+base_processor_id = "nlpconnect/vit-gpt2-image-captioning" # <-- Replace with correct HF ID
 base_model_id = "nlpconnect/vit-gpt2-image-captioning" # <-- Replace with correct HF ID (e.g., Salesforce/blip2-opt-2.7b)
 
 # 2. Specify the PEFT adapter repository ID (this repo)
@@ -47,9 +48,11 @@ processor = AutoProcessor.from_pretrained(base_processor_id)
 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 = AutoModelForCausalLM
+......
 
 # --- Load PEFT Adapter ---
 # Load the adapter config and merge the adapter weights into the base model
@@ -60,16 +63,15 @@ model.eval() # Set model to evaluation mode
 # --- Inference Example ---
 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
-#
+
 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}}")
-
 ```
 
 *More model-specific documentation, evaluation results, and usage examples should be added here.*