Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -1,48 +1,36 @@
|
|
1 |
import gradio as gr
|
2 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
3 |
|
4 |
-
# Load
|
5 |
model_name = "iqrabatool/finetuned_LLaMA"
|
6 |
-
model = AutoModelForCausalLM.from_pretrained(model_name)
|
7 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
8 |
|
9 |
-
def respond(
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
max_tokens,
|
14 |
-
temperature,
|
15 |
-
top_p,
|
16 |
-
):
|
17 |
-
messages = [{"role": "system", "content": system_message}]
|
18 |
-
|
19 |
-
for val in history:
|
20 |
-
if val[0]:
|
21 |
-
messages.append({"role": "user", "content": val[0]})
|
22 |
-
if val[1]:
|
23 |
-
messages.append({"role": "assistant", "content": val[1]})
|
24 |
-
|
25 |
-
messages.append({"role": "user", "content": message})
|
26 |
-
|
27 |
-
inputs = tokenizer(message, return_tensors="pt")
|
28 |
-
outputs = model.generate(**inputs, max_length=max_tokens, temperature=temperature, top_p=top_p)
|
29 |
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
30 |
return response
|
31 |
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
|
|
|
|
|
|
|
|
46 |
)
|
47 |
|
48 |
if __name__ == "__main__":
|
|
|
1 |
import gradio as gr
|
2 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
3 |
|
4 |
+
# Load model and tokenizer from Hugging Face
|
5 |
model_name = "iqrabatool/finetuned_LLaMA"
|
6 |
+
model = AutoModelForCausalLM.from_pretrained(model_name, use_auth_token=True)
|
7 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
8 |
|
9 |
+
def respond(message, system_message, max_tokens, temperature, top_p):
|
10 |
+
# Generate response
|
11 |
+
inputs = tokenizer(message, return_tensors="pt", max_length=max_tokens, truncation=True, padding=True)
|
12 |
+
outputs = model.generate(**inputs, temperature=temperature, top_p=top_p)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
14 |
return response
|
15 |
|
16 |
+
# Define interface components
|
17 |
+
additional_inputs = [
|
18 |
+
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
|
19 |
+
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
|
20 |
+
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
|
21 |
+
gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
|
22 |
+
]
|
23 |
+
|
24 |
+
# Create the ChatInterface
|
25 |
+
demo = gr.Interface(
|
26 |
+
fn=respond,
|
27 |
+
inputs=["text", "text", "number", "number", "number"],
|
28 |
+
outputs="text",
|
29 |
+
title="Health Bot",
|
30 |
+
description="A chatbot for health-related inquiries.",
|
31 |
+
article="The Health Bot assists users with health-related questions and provides information based on a pre-trained language model.",
|
32 |
+
examples=[["What are the symptoms of COVID-19?", "Health Bot: COVID-19 symptoms include..."]],
|
33 |
+
additional_inputs=additional_inputs
|
34 |
)
|
35 |
|
36 |
if __name__ == "__main__":
|