Spaces:
Runtime error
Runtime error
File size: 2,831 Bytes
a9f3611 be82d2e 7cc1dd3 14ea75d ea7122b e928714 7cc1dd3 ea7122b e928714 7cc1dd3 e928714 7cc1dd3 e928714 7cc1dd3 e928714 7cc1dd3 |
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 |
import os
os.system('pip install minijinja')
import gradio as gr
from huggingface_hub import InferenceClient
import torch
import spaces
# Initialize the client with your model
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta") # Replace with your model's name or endpoint
default_system = 'You are a helpful assistant'
@spaces.GPU
def respond(message, history, system_message, max_tokens, temperature, top_p):
messages = [{"role": "system", "content": system_message}]
for user, assistant in history:
messages.append({"role": "user", "content": user})
messages.append({"role": "assistant", "content": assistant})
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
def clear_session():
return "", []
def modify_system_session(system):
if not system:
system = default_system
return system, system, []
with gr.Blocks() as demo:
gr.Markdown("<h1 style='text-align: center;'>LLM.C 1.5B Chat Demo 🤖</h1>")
with gr.Row():
with gr.Column(scale=3):
system_input = gr.Textbox(value=default_system, lines=1, label='System Prompt')
with gr.Column(scale=3):
modify_system = gr.Button("🛠️ Set system prompt and clear history")
system_state = gr.Textbox(value=default_system, visible=False)
chatbot = gr.Chatbot(label='LLM.C Chat')
message = gr.Textbox(lines=1, label='Your message')
with gr.Row():
clear_history = gr.Button("🧹 Clear history")
submit = gr.Button("🚀 Send")
with gr.Accordion("Advanced Settings", open=False):
max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max New Tokens")
temperature = gr.Slider(minimum=0.1, maximum=2.0, 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)")
# Set up event handlers
message.submit(respond, inputs=[message, chatbot, system_state, max_tokens, temperature, top_p], outputs=[chatbot])
submit.click(respond, inputs=[message, chatbot, system_state, max_tokens, temperature, top_p], outputs=[chatbot])
clear_history.click(fn=clear_session, inputs=[], outputs=[message, chatbot])
modify_system.click(fn=modify_system_session, inputs=[system_input], outputs=[system_state, system_input, chatbot])
gr.Markdown(
"""
## About LLM.C
Some stuff about llm.c + link to the github repo
"""
)
if __name__ == "__main__":
demo.launch() |