"Update space"

Signed-off-by: Emmanuel Frimpong Asante <[email protected]>

app.py

@@ -98,6 +98,10 @@ model_name = "meta-llama/Llama-2-7b-chat-hf"  # Example model name; replace with
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
 
+# Set the padding token to EOS token or add a new padding token
+if tokenizer.pad_token is None:
+    tokenizer.add_special_tokens({'pad_token': '[PAD]'})
+    model.resize_token_embeddings(len(tokenizer))
 
 # Define Llama 2 response generation
 def llama2_response(user_input):
@@ -108,7 +112,7 @@ def llama2_response(user_input):
             max_length=150,
             do_sample=True,
             temperature=0.7,
-            pad_token_id=tokenizer.eos_token_id,
+            pad_token_id=tokenizer.pad_token_id,  # Use the newly set padding token
             attention_mask=inputs["attention_mask"]
         )