File size: 1,264 Bytes
d5cf576
 
 
 
 
aa18589
 
 
 
 
 
 
 
 
 
 
 
 
d5cf576
5497dbb
aa18589
 
 
 
164b08e
52c4d17
aa18589
d5cf576
 
 
 
aa18589
 
d5cf576
aa18589
d5cf576
 
fe49e01
d5cf576
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
import gradio as gr
from huggingface_hub import InferenceClient

client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")

def format_alpaca_prompt(user_input, system_prompt):
    """Formats input in Alpaca/LLaMA style"""
    prompt = f"""{system_prompt}

### Instruction:
{user_input}

### Response:
"""
    return prompt

def respond(message, history, system_message, max_tokens, temperature, top_p):
    formatted_prompt = format_alpaca_prompt(message, system_message)

    response = client.text_generation(
        formatted_prompt,  # βœ… Pass as a single string
        max_new_tokens=max_tokens,  # βœ… Use max_new_tokens, not max_tokens
        temperature=temperature,
        top_p=top_p,
    )

    yield response  # βœ… Output the generated response

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=250, value=128, step=1, label="Max new tokens"),  # βœ… Keep ≀250
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
    ],
)

if __name__ == "__main__":
    demo.launch()