Spaces:
Runtime error
Runtime error
File size: 1,839 Bytes
5456c1a e7f0203 5456c1a f7094c4 5456c1a f7094c4 5456c1a e7f0203 f7094c4 e7f0203 f7094c4 e7f0203 f7094c4 e7f0203 5456c1a e7f0203 5456c1a f7094c4 5456c1a e7f0203 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
# Load the ClinicalBERT model
MODEL_NAME = "emilyalsentzer/Bio_ClinicalBERT"
client = InferenceClient(MODEL_NAME)
def respond(
message,
history,
system_message,
max_tokens,
temperature,
top_p,
):
if history is None:
history = []
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
# Ensure input includes [MASK] for ClinicalBERT
if "[MASK]" not in message:
message += " [MASK]"
try:
response = client.fill_mask(message)
prediction = response[0]["sequence"]
confidence = response[0]["score"]
# Append to history
history.append((message, prediction))
return prediction, history # Must return history explicitly as an output
except Exception as e:
return {"error": str(e)}, history
# Create Gradio interface
demo = gr.Interface(
fn=respond,
inputs=[
gr.Textbox(label="User Input"),
gr.State(), # Explicit state for history tracking
gr.Textbox(value="You are a friendly medical assistant.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p"),
],
outputs=[
gr.Textbox(label="Model Response"),
gr.State(), # Explicit state output
],
)
if __name__ == "__main__":
demo.launch(share=True)
|