Spaces:
Sleeping
Sleeping
changed model
Browse files
app.py
CHANGED
@@ -7,7 +7,25 @@ from huggingface_hub import InferenceClient
|
|
7 |
"""
|
8 |
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
|
9 |
"""
|
10 |
-
client = InferenceClient("google/gemma-3-27b-it", token=os.getenv("TOKEN"))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
|
12 |
global history
|
13 |
history = []
|
@@ -31,8 +49,10 @@ async def respond(
|
|
31 |
|
32 |
response = ""
|
33 |
|
34 |
-
for message in client.chat_completion(
|
35 |
-
|
|
|
|
|
36 |
max_tokens=max_tokens,
|
37 |
stream=True,
|
38 |
temperature=temperature,
|
|
|
7 |
"""
|
8 |
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
|
9 |
"""
|
10 |
+
#client = InferenceClient("google/gemma-3-27b-it", token=os.getenv("TOKEN"))
|
11 |
+
|
12 |
+
client = InferenceClient(
|
13 |
+
provider="fireworks-ai",
|
14 |
+
api_key=os.getenv("TOKEN"),
|
15 |
+
)
|
16 |
+
|
17 |
+
# completion = client.chat.completions.create(
|
18 |
+
# model="deepseek-ai/DeepSeek-V3-0324",
|
19 |
+
# messages=[
|
20 |
+
# {
|
21 |
+
# "role": "user",
|
22 |
+
# "content": "What is the capital of France?"
|
23 |
+
# }
|
24 |
+
# ],
|
25 |
+
# max_tokens=500,
|
26 |
+
# )
|
27 |
+
|
28 |
+
# print(completion.choices[0].message)
|
29 |
|
30 |
global history
|
31 |
history = []
|
|
|
49 |
|
50 |
response = ""
|
51 |
|
52 |
+
#for message in client.chat_completion(
|
53 |
+
for message in client.chat.completions.create(
|
54 |
+
model="deepseek-ai/DeepSeek-V3-0324",
|
55 |
+
messages=messages,
|
56 |
max_tokens=max_tokens,
|
57 |
stream=True,
|
58 |
temperature=temperature,
|