Update README.md

README.md

@@ -68,14 +68,18 @@ import torch
 from llm2vec_wrapper import LLM2VecWrapper as LLM2Vec
 
 # Load the model - latent attention weights are automatically loaded!
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 model = LLM2Vec.from_pretrained(
     base_model_name_or_path='lukeingawesome/llm2vec4cxr',
-    pooling_mode="latent_attention",  # This automatically loads the trained weights
+    pooling_mode="latent_attention",
     max_length=512,
     enable_bidirectional=True,
     torch_dtype=torch.bfloat16,
     use_safetensors=True,
-)
+).to(device).eval()
+
+# Configure tokenizer
+model.tokenizer.padding_side = 'left'
 
 # Simple text encoding
 report = "There is a small increase in the left-sided effusion. There continues to be volume loss at both bases."
@@ -125,12 +129,18 @@ import torch
 from llm2vec_wrapper import LLM2VecWrapper as LLM2Vec
 
 # Load model
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 model = LLM2Vec.from_pretrained(
-    'lukeingawesome/llm2vec4cxr',
+    base_model_name_or_path='lukeingawesome/llm2vec4cxr',
     pooling_mode="latent_attention",
+    max_length=512,
+    enable_bidirectional=True,
     torch_dtype=torch.bfloat16,
     use_safetensors=True,
-)
+).to(device).eval()
+
+# Configure tokenizer
+model.tokenizer.padding_side = 'left'
 
 # Medical text analysis
 instruction = 'Determine the change or the status of the pleural effusion.'