Update app.py
Browse files
app.py
CHANGED
@@ -4,7 +4,10 @@ from huggingface_hub import InferenceClient
|
|
4 |
"""
|
5 |
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
|
6 |
"""
|
7 |
-
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
|
|
|
|
|
|
|
8 |
|
9 |
|
10 |
def respond(
|
@@ -27,17 +30,16 @@ def respond(
|
|
27 |
|
28 |
response = ""
|
29 |
|
30 |
-
|
|
|
31 |
messages,
|
32 |
max_tokens=max_tokens,
|
33 |
-
stream=True,
|
34 |
temperature=temperature,
|
35 |
top_p=top_p,
|
36 |
-
)
|
37 |
-
|
38 |
|
39 |
-
|
40 |
-
yield response
|
41 |
|
42 |
|
43 |
"""
|
@@ -61,4 +63,4 @@ demo = gr.ChatInterface(
|
|
61 |
|
62 |
|
63 |
if __name__ == "__main__":
|
64 |
-
demo.launch()
|
|
|
4 |
"""
|
5 |
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
|
6 |
"""
|
7 |
+
#client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
|
8 |
+
#client = InferenceClient("meta-llama/Llama-3.2-1B-Instruct")
|
9 |
+
#client = InferenceClient("microsoft/Phi-3.5-mini-instruct")
|
10 |
+
client = InferenceClient("unsloth/Llama-3.2-1B-Instruct")
|
11 |
|
12 |
|
13 |
def respond(
|
|
|
30 |
|
31 |
response = ""
|
32 |
|
33 |
+
|
34 |
+
mensagens = client.chat_completion(
|
35 |
messages,
|
36 |
max_tokens=max_tokens,
|
|
|
37 |
temperature=temperature,
|
38 |
top_p=top_p,
|
39 |
+
)
|
40 |
+
response = mensagens.choices[0].message.content
|
41 |
|
42 |
+
return response
|
|
|
43 |
|
44 |
|
45 |
"""
|
|
|
63 |
|
64 |
|
65 |
if __name__ == "__main__":
|
66 |
+
demo.launch()
|