Upload app.py

app.py

@@ -0,0 +1,20 @@
+import streamlit as st
+from transformers import AutoTokenizer, LlamaForCausalLM
+
+@st.cache(allow_output_mutation=True)
+def load_model():
+    model = LlamaForCausalLM.from_pretrained(/code/Weights/)
+    tokenizer = AutoTokenizer.from_pretrained(/code/Tokenizer/tokenizer.model)
+    return model, tokenizer
+
+model, tokenizer = load_model()
+
+st.title("Chat with LlamaForCausalLM Model")
+
+user_input = st.text_input("Type your message", "")
+
+if st.button("Send"):
+    inputs = tokenizer(user_input, return_tensors="pt")
+    generate_ids = model.generate(inputs.input_ids, max_length=30)
+    response = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+    st.write(response)