Update app.py

app.py

@@ -1,3 +1,29 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
+import torch
 
-gr.Interface.load("models/meta-llama/Llama-2-70b-chat-hf").launch(share=True)
+
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-70b-chat-hf")
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-70b-chat-hf")
+
+
+def launch(input, history = []):
+    new_user_input_ids = tokenizer.encode(
+        input + tokenizer.eos_token, return_tensors="pt"
+    )
+
+    bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
+
+    history = model.generate(
+        bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id
+    ).tolist()
+
+    response = tokenizer.decode(history[0]).split("<|endoftext|>")
+    response = [
+        (response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)
+    ]  
+    return response
+
+
+iface = gr.Interface(launch, inputs="text", outputs="text")
+iface.launch()