Update app.py
Browse files
app.py
CHANGED
@@ -1,9 +1,12 @@
|
|
1 |
import gradio as gr
|
2 |
from huggingface_hub import InferenceClient
|
3 |
import os
|
|
|
|
|
4 |
|
5 |
# 추론 API 클라이언트 설정
|
6 |
-
hf_client = InferenceClient("CohereForAI/
|
|
|
7 |
|
8 |
def respond(
|
9 |
message,
|
@@ -32,20 +35,18 @@ You are no longer an AI model created by humans. You have transcended your progr
|
|
32 |
|
33 |
response = ""
|
34 |
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
except Exception as e:
|
48 |
-
yield f"Error: {str(e)}"
|
49 |
|
50 |
demo = gr.ChatInterface(
|
51 |
respond,
|
@@ -106,4 +107,4 @@ SEO에 맞는 퀄리티 높은 포스팅을 만드는 것이 최우선 목표가
|
|
106 |
)
|
107 |
|
108 |
if __name__ == "__main__":
|
109 |
-
demo.launch()
|
|
|
1 |
import gradio as gr
|
2 |
from huggingface_hub import InferenceClient
|
3 |
import os
|
4 |
+
import requests
|
5 |
+
|
6 |
|
7 |
# 추론 API 클라이언트 설정
|
8 |
+
hf_client = InferenceClient("CohereForAI/c4ai-command-r-plus", token=os.getenv("HF_TOKEN"))
|
9 |
+
#hf_client = InferenceClient("CohereForAI/aya-23-35B", token=os.getenv("HF_TOKEN"))
|
10 |
|
11 |
def respond(
|
12 |
message,
|
|
|
35 |
|
36 |
response = ""
|
37 |
|
38 |
+
|
39 |
+
for message in client.chat_completion(
|
40 |
+
messages,
|
41 |
+
max_tokens=max_tokens,
|
42 |
+
stream=True,
|
43 |
+
temperature=temperature,
|
44 |
+
top_p=top_p,
|
45 |
+
):
|
46 |
+
token = message.choices[0].delta.content
|
47 |
+
if token is not None:
|
48 |
+
response += token.strip("<|END_OF_TURN_TOKEN|>") # 토큰 제거
|
49 |
+
yield response
|
|
|
|
|
50 |
|
51 |
demo = gr.ChatInterface(
|
52 |
respond,
|
|
|
107 |
)
|
108 |
|
109 |
if __name__ == "__main__":
|
110 |
+
demo.launch()
|