Update app.py
Browse files
app.py
CHANGED
@@ -5,7 +5,7 @@ api_key=os.environ.get('qwen_API_KEY')
|
|
5 |
"""
|
6 |
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
|
7 |
"""
|
8 |
-
client = InferenceClient(api_key
|
9 |
|
10 |
|
11 |
def respond(
|
@@ -29,13 +29,12 @@ def respond(
|
|
29 |
response = ""
|
30 |
|
31 |
for message in client.chat_completion(
|
32 |
-
model="Qwen/Qwen2.5-72B-Instruct",
|
33 |
messages,
|
34 |
max_tokens=max_tokens,
|
35 |
stream=True,
|
36 |
temperature=temperature,
|
37 |
top_p=top_p,
|
38 |
-
)
|
39 |
token = message.choices[0].delta.content
|
40 |
|
41 |
response += token
|
|
|
5 |
"""
|
6 |
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
|
7 |
"""
|
8 |
+
client = InferenceClient("Qwen/Qwen2.5-72B-Instruct",api_key)
|
9 |
|
10 |
|
11 |
def respond(
|
|
|
29 |
response = ""
|
30 |
|
31 |
for message in client.chat_completion(
|
|
|
32 |
messages,
|
33 |
max_tokens=max_tokens,
|
34 |
stream=True,
|
35 |
temperature=temperature,
|
36 |
top_p=top_p,
|
37 |
+
):
|
38 |
token = message.choices[0].delta.content
|
39 |
|
40 |
response += token
|