Spaces:
Running
Running
File size: 1,520 Bytes
9cfe82c 4a20f72 2137129 4a20f72 2137129 4a20f72 2137129 65f055c 4a20f72 2137129 ef1a69d 2137129 e908972 4a20f72 2137129 9cfe82c fb97bf4 65f055c 506a058 74e3d53 9cfe82c ee43960 4a20f72 2137129 |
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 42 43 44 45 46 47 |
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, history):
"""Formats input in Alpaca/LLaMA style"""
history_str = "\n".join([f"### Instruction:\n{h[0]}\n### Response:\n{h[1]}" for h in history])
prompt = f"""{system_prompt}
{history_str}
### 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, history)
response = client.text_generation(
formatted_prompt,
max_new_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
)
# ✅ Extract only the response
cleaned_response = response.split("### Response:")[-1].strip()
history.append((message, cleaned_response)) # ✅ Update history with the new message and response
yield cleaned_response # ✅ Output only the answer
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"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.9, step=0.1, label="Temperature"),
gr.Slider(minimum=0.1, maximum=1.0, value=0.99, step=0.01, label="Top-p (nucleus sampling)"),
],
)
if __name__ == "__main__":
demo.launch() |