Upload folder using huggingface_hub

README.md

@@ -21,26 +21,25 @@ library_name: peft
 
 ## Uses
 
-This model is finetuned from `vidore/colpali-v1.2` using the PEFT library. To use this model, you can use the following code:
+This model is finetuned from `vidore/colpali-v1.2` using the PEFT library. To use this model, you only need to change the path ColPali is loaded from.
 
 ```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-from peft import PeftModel
+device = get_torch_device("auto")
+print(f"Device used: {device}")
 
-### This will load the basemodel ###
-# Load the base model
-model_name = "colpali_finetuned"
-model = AutoModelForCausalLM.from_pretrained(model_name)
+# Model name
+model_name = "path/to/fine_tuned_model"
 
-# Load the tokenizer
-tokenizer = AutoTokenizer.from_pretrained(model_name)
+# Load model
+model = ColPali.from_pretrained(
+    model_name,
+    torch_dtype=torch.bfloat16,
+    device_map=device,
+).eval()
 
+# Load processor
+processor = cast(ColPaliProcessor, ColPaliProcessor.from_pretrained(model_name))
 
-### This will load the adapter model ###
-
-peft_model_path='colpali_finetuned/checkpoint-587'
-model = PeftModel.from_pretrained(peft_model_path)
 ```
 
-
 - PEFT 0.11.1