Spaces:
Running
Running
File size: 2,329 Bytes
1b9e6e3 421af5a 2bfec82 421af5a 2bfec82 421af5a ad1b48b 421af5a 846f316 421af5a 224ca32 1aa416c 16832a6 224ca32 1b9e6e3 421af5a 1b9e6e3 2bfec82 846f316 363ecd9 2bfec82 363ecd9 2bfec82 1b9e6e3 363ecd9 |
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 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 |
import gradio as gr
from huggingface_hub import InferenceClient
# Custom background CSS with semi-transparent panel
css = """
body {
background-image: url('https://cdn-uploads.huggingface.co/production/uploads/67351c643fe51cb1aa28f2e5/wuyd5UYTh9jPrMJGmV9yC.jpeg');
background-size: cover;
background-position: center;
background-repeat: no-repeat;
}
#chat-panel {
background-color: rgba(255, 255, 255, 0.85);
padding: 2rem;
border-radius: 12px;
max-width: 700px;
height: 70vh;
margin: auto;
box-shadow: 0 0 12px rgba(0, 0, 0, 0.3);
overflow-y: auto;
}
#chat-title {
color: #856966;
font-family: 'Playfair Display', serif;
font-size: 1.8rem;
font-weight: bold;
text-align: center;
margin-bottom: 1rem;
}
"""
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
response = ""
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content
response += token
yield response
with gr.Blocks(css=css) as demo:
with gr.Column(elem_id="chat-panel"):
gr.Markdown("## 🇫🇷 French Tutor")
with gr.Accordion("⚙️ Settings", open=False):
system_message = gr.Textbox(value="You are a friendly Chatbot.", label="System message")
max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")
gr.ChatInterface(
respond,
additional_inputs=[system_message, max_tokens, temperature, top_p]
)
if __name__ == "__main__":
demo.launch() |