Spaces:
Sleeping
Sleeping
fix 5
Browse files
app.py
CHANGED
|
@@ -6,8 +6,10 @@ from huggingface_hub import InferenceClient
|
|
| 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 |
|
|
|
|
| 9 |
huggingface_token = os.getenv("SECRET_ENV_VARIABLE")
|
| 10 |
-
client = InferenceClient(api_key=huggingface_token)
|
|
|
|
| 11 |
|
| 12 |
'''
|
| 13 |
import requests
|
|
@@ -45,8 +47,7 @@ def respond(
|
|
| 45 |
response = ""
|
| 46 |
|
| 47 |
for message in client.chat_completion(
|
| 48 |
-
|
| 49 |
-
messages=messages,
|
| 50 |
max_tokens=max_tokens,
|
| 51 |
stream=True,
|
| 52 |
temperature=temperature,
|
|
|
|
| 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 |
|
| 9 |
+
model_name = "meta-llama/Llama-3.2-1B"
|
| 10 |
huggingface_token = os.getenv("SECRET_ENV_VARIABLE")
|
| 11 |
+
#client = InferenceClient(api_key=huggingface_token)
|
| 12 |
+
client = InferenceClient(model=model_name, token=huggingface_token)
|
| 13 |
|
| 14 |
'''
|
| 15 |
import requests
|
|
|
|
| 47 |
response = ""
|
| 48 |
|
| 49 |
for message in client.chat_completion(
|
| 50 |
+
messages,
|
|
|
|
| 51 |
max_tokens=max_tokens,
|
| 52 |
stream=True,
|
| 53 |
temperature=temperature,
|