Create app.py

app.py

@@ -0,0 +1,26 @@
+import streamlit as st
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+@st.cache(allow_output_mutation=True)
+def load_model():
+    model_id = "Tech-Meld/Hajax_Chat_1.0-Q3_K_S-GGUF"
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    model = AutoModelForCausalLM.from_pretrained(model_id)
+    return model, tokenizer
+
+def get_response(input_text, model, tokenizer):
+    inputs = tokenizer.encode(input_text + tokenizer.eos_token, return_tensors='pt')
+    outputs = model.generate(inputs, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+    response = tokenizer.decode(outputs[:, inputs.shape[-1]:][0], skip_special_tokens=True)
+    return response
+
+def main():
+    model, tokenizer = load_model()
+    st.title("Chat with AI")
+    input_text = st.text_input("You: ", "")
+    if st.button("Send"):
+        response = get_response(input_text, model, tokenizer)
+        st.text_area("AI: ", response)
+
+if __name__ == "__main__":
+    main()