Update README.md

README.md

@@ -39,7 +39,7 @@ def get_embedding(last_hidden_state: torch.Tensor, attention_mask: torch.Tensor)
 ### Encode Text Query
 
 ```python
-queries = ["query: Where can we find Llama?", "query: What is the LLaMA model?"]
+queries = ["query: Where can we see Llama?", "query: What is LLaMA model?"]
 query_inputs = processor(queries, return_tensors="pt", padding="longest", max_length=128, truncation=True).to('cuda:0')
 output = model(**query_inputs, return_dict=True, output_hidden_states=True)
 query_embeddings = get_embedding(output.hidden_states[-1], query_inputs["attention_mask"])
@@ -49,12 +49,24 @@ query_embeddings = get_embedding(output.hidden_states[-1], query_inputs["attenti
 
 ```python
 from PIL import Image
+import requests
+from io import BytesIO
+
+# URLs of the images
+url1 = "https://huggingface.co/Tevatron/dse-phi3-docmatix-v1.0/blob/main/animal-llama.png"
+url2 = "https://huggingface.co/Tevatron/dse-phi3-docmatix-v1.0/blob/main/meta-llama.png"
+
+# Download and open images
+response1 = requests.get(url1)
+response2 = requests.get(url2)
+
+passage_image1 = Image.open(BytesIO(response1.content))
+passage_image2 = Image.open(BytesIO(response2.content))
 
-passage_image1 = Image.open("path/to/your/image1.png")
-passage_image2 = Image.open("path/to/your/image2.png")
 passage_images = [passage_image1, passage_image2]
 passage_prompts = ["\nWhat is shown in this image?</s>", "\nWhat is shown in this image?</s>"]
 
+# Process inputs and get embeddings
 passage_inputs = processor(passage_prompts, images=passage_images, return_tensors="pt", padding="longest", max_length=4096, truncation=True).to('cuda:0')
 output = model(**passage_inputs, return_dict=True, output_hidden_states=True)
 doc_embeddings = get_embedding(output.hidden_states[-1], passage_inputs["attention_mask"])
@@ -72,7 +84,10 @@ print(similarities)
 ### Encode Document Text
 This DSE checkpoint is warm-up with `Tevatron/msmarco-passage-aug`, thus the model can also effectively encode document as text input.
 ```python
-passage_prompts = ["Llama is in Aferica</s>", "LLaMA is an LLM released by Meta.</s>"]
+passage_prompts = [
+  "The llama (/ˈlɑːmə/; Spanish pronunciation: [ˈʎama] or [ˈʝama]) (Lama glama) is a domesticated South American camelid, widely used as a meat and pack animal by Andean cultures since the pre-Columbian era.</s>",
+  "Llama (acronym for Large Language Model Meta AI, and formerly stylized as LLaMA) is a family of autoregressive large language models (LLMs) released by Meta AI starting in February 2023.[2][3] The latest version is Llama 3.1, released in July 2024.[4]"
+]
 
 passage_inputs = processor(passage_prompts, images=None, return_tensors="pt", padding="longest", max_length=4096, truncation=True).to('cuda:0')
 output = model(**passage_inputs, return_dict=True, output_hidden_states=True)