Spaces:
Runtime error
Runtime error
Goekdeniz-Guelmez
commited on
Commit
•
fb1f1d4
1
Parent(s):
502ca38
Add application file
Browse files
app.py
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
from transformers import AutoTokenizer, pipeline
|
3 |
+
import torch
|
4 |
+
|
5 |
+
# Initialize the model and tokenizer
|
6 |
+
model = "Isaak-Carter/JOSIE_Beta-5-7B-slerp"
|
7 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
8 |
+
|
9 |
+
ai_pipeline = transformers.pipeline(
|
10 |
+
"text-generation",
|
11 |
+
model=model_name,
|
12 |
+
torch_dtype=torch.float16,
|
13 |
+
device_map="auto",
|
14 |
+
)
|
15 |
+
|
16 |
+
def generate_response(user_input):
|
17 |
+
"""
|
18 |
+
Generate a response to the user input using the specified AI model.
|
19 |
+
|
20 |
+
Args:
|
21 |
+
user_input (str): The question or prompt from the user.
|
22 |
+
|
23 |
+
Returns:
|
24 |
+
str: The generated response from the AI model.
|
25 |
+
"""
|
26 |
+
messages = [{"role": "user", "content": user_input}]
|
27 |
+
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
28 |
+
|
29 |
+
pipeline = transformers.pipeline(
|
30 |
+
"text-generation",
|
31 |
+
model=model,
|
32 |
+
torch_dtype=torch.float16,
|
33 |
+
device_map="auto",
|
34 |
+
)
|
35 |
+
|
36 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
37 |
+
|
38 |
+
return outputs[0]["generated_text"]
|
39 |
+
|
40 |
+
# Create Gradio interface
|
41 |
+
interface = gr.Interface(fn=generate_response, inputs="text", outputs="text", title="JOSIE Beta 5", description="Asc JOSIE Beta 5.")
|
42 |
+
interface.launch()
|
43 |
+
|