Spaces:
Running
Running
a100 kh
commited on
Commit
•
4f21439
1
Parent(s):
b8c3f0e
app.py
CHANGED
|
@@ -5,7 +5,7 @@ from openai import OpenAI
|
|
| 5 |
# Modify OpenAI's API key and API base to use vLLM's API server.
|
| 6 |
openai_api_key = "12345"
|
| 7 |
openai_api_base = "https://a502-131-112-63-87.ngrok-free.app/v1"
|
| 8 |
-
|
| 9 |
"""
|
| 10 |
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
|
| 11 |
"""
|
|
@@ -36,8 +36,9 @@ def respond(
|
|
| 36 |
|
| 37 |
response = ""
|
| 38 |
|
| 39 |
-
for message in client.
|
| 40 |
-
|
|
|
|
| 41 |
max_tokens=max_tokens,
|
| 42 |
stream=True,
|
| 43 |
temperature=temperature,
|
|
|
|
| 5 |
# Modify OpenAI's API key and API base to use vLLM's API server.
|
| 6 |
openai_api_key = "12345"
|
| 7 |
openai_api_base = "https://a502-131-112-63-87.ngrok-free.app/v1"
|
| 8 |
+
model_name = "cyberagent/calm3-22b-chat"
|
| 9 |
"""
|
| 10 |
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
|
| 11 |
"""
|
|
|
|
| 36 |
|
| 37 |
response = ""
|
| 38 |
|
| 39 |
+
for message in client.chat.completions.create(
|
| 40 |
+
model_name=model_name,
|
| 41 |
+
messages=messages,
|
| 42 |
max_tokens=max_tokens,
|
| 43 |
stream=True,
|
| 44 |
temperature=temperature,
|