Upload 2 files

main.py

@@ -0,0 +1,52 @@
+import streamlit as st
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+
+# Define the path where the model and tokenizer are saved
+save_directory = "RAG_model"
+
+
+# Load the model and tokenizer from the saved directory
+@st.cache(allow_output_mutation=True)
+def load_model():
+    model = AutoModelForCausalLM.from_pretrained(save_directory)
+    tokenizer = AutoTokenizer.from_pretrained(save_directory)
+    return model, tokenizer
+
+
+model, tokenizer = load_model()
+
+# Set up the text generation pipeline
+query_pipeline = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    device=-1,  # Use CPU
+    device_map="auto",
+)
+
+st.title("Text Generation with Llama-2 Model")
+st.write("This is a simple Streamlit app to generate text using the Llama-2 model.")
+
+# Text input for the user
+user_input = st.text_area("Enter your prompt:", "")
+
+# Generate text when the user clicks the button
+if st.button("Generate"):
+    if user_input:
+        with st.spinner("Generating..."):
+            sequences = query_pipeline(
+                user_input,
+                do_sample=True,
+                top_k=10,
+                num_return_sequences=1,
+                eos_token_id=tokenizer.eos_token_id,
+                max_length=200,
+            )
+            for seq in sequences:
+                st.write("Generated text:")
+                st.write(seq['generated_text'])
+    else:
+        st.write("Please enter a prompt to generate text.")
+
+# Add an example usage
+st.write("Example usage: Enter a prompt like 'What is Artificial Intelligence?' and click 'Generate'.")

requirements.txt

@@ -0,0 +1,12 @@
+sentence-transformers
+transformers
+accelerate
+einops==0.6.1
+langchain==0.0.300
+bitsandbytes==0.41.1
+sentence_transformers==2.2.2
+chromadb
+faiss-cpu
+git+https://github.com/huggingface/accelerate.git
+git+https://github.com/huggingface/transformers.git
+bitsandbytes