Spaces:
Sleeping
Sleeping
File size: 1,001 Bytes
dd7ea12 5698eae dd7ea12 5698eae dd7ea12 |
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 |
import gradio as gr
from ctransformers import AutoModelForCausalLM
import time
llm = AutoModelForCausalLM.from_pretrained(
"TheBloke/WizardCoder-Python-7B-V1.0-GGUF",
model_file="wizardcoder-python-7b-v1.0.Q4_K_M.gguf",
model_type="llama",
max_new_tokens=512,
temperature=0.7,
top_p=0.9,
stream=True
)
def generate_response(message, history):
prompt = ""
for user, bot in history:
prompt += f"<user>: {user}\n<assistant>: {bot}\n"
prompt += f"<user>: {message}\n<assistant>:"
history.append([message, ""])
response = ""
for chunk in llm(prompt):
response += chunk
history[-1][1] = response
time.sleep(0.01)
yield history
with gr.Blocks() as demo:
chatbot = gr.Chatbot()
msg = gr.Textbox(placeholder="Ask coding questions...", label="Your Message")
clear = gr.Button("Clear")
msg.submit(generate_response, [msg, chatbot], chatbot)
clear.click(lambda: [], None, chatbot)
demo.launch()
|