SimBombeRino commited on
Commit
27507fb
·
verified ·
1 Parent(s): c59570e

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +12 -16
app.py CHANGED
@@ -1,24 +1,20 @@
1
  import gradio as gr
2
  from huggingface_hub import InferenceClient
3
 
4
- client = InferenceClient("unsloth/llama-3.2-3b-instruct-bnb-4bit", timeout=30)
5
- def respond(message, max_tokens, temperature, top_p):
6
- response = ""
7
-
8
- # Use the text generation API
9
- for message in client.text_generation(
10
- message,
11
- max_new_tokens=max_tokens,
12
- temperature=temperature,
13
- top_p=top_p,
14
- stream=True
15
- ):
16
- token = message["generated_text"]
17
- response += token
18
- yield response
19
 
 
 
 
 
 
 
 
 
 
 
 
20
 
21
- # Create Gradio Interface
22
  demo = gr.Interface(
23
  fn=respond,
24
  inputs=[
 
1
  import gradio as gr
2
  from huggingface_hub import InferenceClient
3
 
4
+ client = InferenceClient("unsloth/llama-3.2-3b-instruct-bnb-4bit", timeout=120)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
 
6
+ def respond(message, max_tokens, temperature, top_p):
7
+ try:
8
+ result = client.text_generation(
9
+ message,
10
+ max_new_tokens=max_tokens,
11
+ temperature=temperature,
12
+ top_p=top_p
13
+ )
14
+ return result["generated_text"]
15
+ except Exception as e:
16
+ return f"Error: {e}"
17
 
 
18
  demo = gr.Interface(
19
  fn=respond,
20
  inputs=[