Spaces:
Sleeping
Sleeping
File size: 3,233 Bytes
efd757b aacdac0 efd757b aacdac0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 |
import streamlit as st
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
import os
# Apply custom CSS for retro 80s green theme
def apply_custom_css():
try:
with open("style.css") as f:
st.markdown(f"<style>{f.read()}</style>", unsafe_allow_html=True)
except FileNotFoundError:
st.warning("style.css not found. Using default styles.")
@st.cache_resource
def load_model():
model_path = "HuggingFaceH4/zephyr-7b-beta"
peft_model_path = "yitzashapiro/FDA-guidance-zephyr-7b-beta-PEFT"
try:
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype=torch.float16 # Adjust if necessary
).eval()
model.load_adapter(peft_model_path)
st.success("Model loaded successfully.")
except Exception as e:
st.error(f"Error loading model: {e}")
st.stop()
return tokenizer, model
def generate_response(tokenizer, model, user_input):
messages = [
{"role": "user", "content": user_input}
]
try:
if hasattr(tokenizer, 'apply_chat_template'):
input_ids = tokenizer.apply_chat_template(
conversation=messages,
max_length=45,
tokenize=True,
add_generation_prompt=True,
return_tensors='pt'
)
else:
input_ids = tokenizer(
user_input,
return_tensors='pt',
truncation=True,
max_length=45
)['input_ids']
pad_token_id = tokenizer.pad_token_id if tokenizer.pad_token_id is not None else 0
attention_mask = (input_ids != pad_token_id).long()
output_ids = model.generate(
input_ids.to(model.device),
max_length=2048,
max_new_tokens=500,
attention_mask=attention_mask.to(model.device)
)
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
return response
except Exception as e:
st.error(f"Error generating response: {e}")
return "An error occurred while generating the response."
def main():
apply_custom_css()
st.set_page_config(page_title="FDA NDA Submission Assistant", layout="centered")
st.title("FDA NDA Submission Assistant")
st.write("Ask the model about submitting an NDA to the FDA.")
tokenizer, model = load_model()
user_input = st.text_input("Enter your question:", "What's the best way to submit an NDA to the FDA?")
if st.button("Generate Response"):
if user_input.strip() == "":
st.error("Please enter a valid question.")
else:
try:
with st.spinner("Generating response..."):
response = generate_response(tokenizer, model, user_input)
st.success("Response:")
st.write(response)
except Exception as e:
st.error(f"An error occurred: {e}")
if __name__ == "__main__":
main() |