Spaces:
Running
on
Zero
Running
on
Zero
Update app.py
Browse files
app.py
CHANGED
@@ -24,7 +24,6 @@ HEADER = """<div style="text-align: center; margin-bottom: 20px;">
|
|
24 |
def respond(
|
25 |
message,
|
26 |
history: list[tuple[str, str]],
|
27 |
-
enable_reasoning,
|
28 |
system_message,
|
29 |
max_tokens,
|
30 |
temperature,
|
@@ -40,7 +39,7 @@ def respond(
|
|
40 |
|
41 |
messages.append({"role": "user", "content": message})
|
42 |
print(messages)
|
43 |
-
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True,
|
44 |
generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=max_tokens, temperature=temperature, repetition_penalty=repetition_penalty)
|
45 |
thread = Thread(target=model.generate, kwargs=generation_kwargs)
|
46 |
|
@@ -54,23 +53,14 @@ chat_interface = gr.ChatInterface(
|
|
54 |
respond,
|
55 |
textbox=gr.Textbox(text_align="right", rtl=True, submit_btn=True, stop_btn=True),
|
56 |
additional_inputs=[
|
57 |
-
gr.Checkbox(label="Enable reasoning", value=False),
|
58 |
gr.Textbox(value="ุฃูุช ูุญููุ ุฐูุงุกู ุงุตุทูุงุนููู ุทูุฑุชู ุดุฑูุฉ 'ูููุฏ'ุ ู
ุชุฎุตุตู ูู ุงูุชูููุฑ ุงูู
ูุทูู ูุงูุชุญููู ุงูุฏููู. ู
ูู
ุชู ุฅููุงู
ุงูู
ุณุชุฎุฏู
ูู ูุฏุนู
ูู
ูู ุฑุญูุชูู
ูุญู ุงูุชุนููู
ุ ุงููู
ูุ ูุชุญููู ุฃูุฏุงููู
ู
ู ุฎูุงู ุชูุฏูู
ุญูููู ุฐููุฉู ูู
ุฏุฑูุณุฉ.", label="System message"),
|
59 |
gr.Slider(minimum=1, maximum=8192, value=4096, step=1, label="Max new tokens"),
|
60 |
gr.Slider(minimum=0.0, maximum=1.0, value=0.6, step=0.1, label="Temperature"),
|
61 |
gr.Slider(minimum=0.0, maximum=2.0, value=1.1, step=0.05, label="Repetition penalty"),
|
62 |
],
|
63 |
-
examples=[["
|
64 |
example_icons=[["๐ก"]],
|
65 |
cache_examples=False,
|
66 |
-
# head="<h1 style='text-align:center;'>Yehia 7B Preview</h1>",
|
67 |
-
# head="Yehia 7B Preview",
|
68 |
-
# css="""
|
69 |
-
# .chat-message {
|
70 |
-
# text-align: right;
|
71 |
-
# direction: rtl;
|
72 |
-
# }
|
73 |
-
# """,
|
74 |
theme="JohnSmith9982/small_and_pretty",
|
75 |
)
|
76 |
|
|
|
24 |
def respond(
|
25 |
message,
|
26 |
history: list[tuple[str, str]],
|
|
|
27 |
system_message,
|
28 |
max_tokens,
|
29 |
temperature,
|
|
|
39 |
|
40 |
messages.append({"role": "user", "content": message})
|
41 |
print(messages)
|
42 |
+
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True, return_dict=True).to(device)
|
43 |
generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=max_tokens, temperature=temperature, repetition_penalty=repetition_penalty)
|
44 |
thread = Thread(target=model.generate, kwargs=generation_kwargs)
|
45 |
|
|
|
53 |
respond,
|
54 |
textbox=gr.Textbox(text_align="right", rtl=True, submit_btn=True, stop_btn=True),
|
55 |
additional_inputs=[
|
|
|
56 |
gr.Textbox(value="ุฃูุช ูุญููุ ุฐูุงุกู ุงุตุทูุงุนููู ุทูุฑุชู ุดุฑูุฉ 'ูููุฏ'ุ ู
ุชุฎุตุตู ูู ุงูุชูููุฑ ุงูู
ูุทูู ูุงูุชุญููู ุงูุฏููู. ู
ูู
ุชู ุฅููุงู
ุงูู
ุณุชุฎุฏู
ูู ูุฏุนู
ูู
ูู ุฑุญูุชูู
ูุญู ุงูุชุนููู
ุ ุงููู
ูุ ูุชุญููู ุฃูุฏุงููู
ู
ู ุฎูุงู ุชูุฏูู
ุญูููู ุฐููุฉู ูู
ุฏุฑูุณุฉ.", label="System message"),
|
57 |
gr.Slider(minimum=1, maximum=8192, value=4096, step=1, label="Max new tokens"),
|
58 |
gr.Slider(minimum=0.0, maximum=1.0, value=0.6, step=0.1, label="Temperature"),
|
59 |
gr.Slider(minimum=0.0, maximum=2.0, value=1.1, step=0.05, label="Repetition penalty"),
|
60 |
],
|
61 |
+
examples=[["ู
ุง ูู ุนุงุตู
ุฉ ููุณุทูู ุ"]],
|
62 |
example_icons=[["๐ก"]],
|
63 |
cache_examples=False,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
64 |
theme="JohnSmith9982/small_and_pretty",
|
65 |
)
|
66 |
|