Update app.py
Browse files
app.py
CHANGED
@@ -4,7 +4,7 @@ from huggingface_hub import InferenceClient
|
|
4 |
"""
|
5 |
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
|
6 |
"""
|
7 |
-
client = InferenceClient("
|
8 |
|
9 |
|
10 |
def respond(
|
@@ -28,6 +28,7 @@ def respond(
|
|
28 |
response = ""
|
29 |
|
30 |
for message in client.chat_completion(
|
|
|
31 |
messages,
|
32 |
max_tokens=max_tokens,
|
33 |
stream=True,
|
@@ -45,8 +46,8 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
|
|
45 |
demo = gr.ChatInterface(
|
46 |
respond,
|
47 |
additional_inputs=[
|
48 |
-
gr.Textbox(value="You are
|
49 |
-
gr.Slider(minimum=1, maximum=
|
50 |
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
|
51 |
gr.Slider(
|
52 |
minimum=0.1,
|
|
|
4 |
"""
|
5 |
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
|
6 |
"""
|
7 |
+
client = InferenceClient(api_key="")
|
8 |
|
9 |
|
10 |
def respond(
|
|
|
28 |
response = ""
|
29 |
|
30 |
for message in client.chat_completion(
|
31 |
+
model="Qwen/Qwen2.5-72B-Instruct",
|
32 |
messages,
|
33 |
max_tokens=max_tokens,
|
34 |
stream=True,
|
|
|
46 |
demo = gr.ChatInterface(
|
47 |
respond,
|
48 |
additional_inputs=[
|
49 |
+
gr.Textbox(value="You are Qwen, created by Alibaba Cloud. You are a helpful assistant.", label="System message"),
|
50 |
+
gr.Slider(minimum=1, maximum=8888, value=2048, step=1, label="Max new tokens"),
|
51 |
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
|
52 |
gr.Slider(
|
53 |
minimum=0.1,
|