Main application

app.py

@@ -0,0 +1,31 @@
+import streamlit as st
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+@st.cache_resource
+def load_model_and_tokenizer(model_id):
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32)
+    return model, tokenizer
+
+def query_model(model_id, question):
+    model, tokenizer = load_model_and_tokenizer(model_id)
+    inputs = tokenizer.encode(question, return_tensors="pt")
+    outputs = model.generate(inputs, max_new_tokens=100)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+model_map = {
+    "FinGPT": "second-state/FinGPT-MT-Llama-3-8B-LoRA-GGUF",
+    "InvestLM": "yixuantt/InvestLM-mistral-AWQ",
+    "FinLlama": "roma2025/FinLlama-3-8B"
+}
+
+st.title("💼 Financial LLM Evaluation Interface")
+
+model_choice = st.selectbox("Select a Financial Model", list(model_map.keys()))
+user_question = st.text_area("Enter your financial question:", "What is the market outlook for the next quarter?")
+
+if st.button("Get Response"):
+    with st.spinner("Generating response..."):
+        try:
+            answer = query_model(model_map[model_choice_