Spaces:
Sleeping
Sleeping
File size: 2,254 Bytes
5c0e14a ba171f6 5c0e14a 8efda6a 5c0e14a a3c8a25 0507dd2 61b8b6c 5c0e14a 0507dd2 5c0e14a 2ada5c8 5c0e14a ba171f6 5c0e14a 4a6ece7 5c0e14a ba171f6 aeeac2d 5cfb556 ba171f6 3319b7e 5c0e14a 54322bd aeeac2d 5c0e14a 698368b |
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 |
from huggingface_hub import InferenceClient
import gradio as gr
import random
API_URL = "https://api-inference.huggingface.co/models/"
client = InferenceClient(
"mistralai/Mistral-7B-Instruct-v0.1"
)
# Flag to track whether initial greeting has been displayed
initial_greeting_displayed = False
def format_prompt(message, history):
global initial_greeting_displayed
prompt = ""
if not initial_greeting_displayed:
prompt += "hi " # Initial greeting
initial_greeting_displayed = True
prompt += "You are BibleLearnerAI, a Christian Bible AI. You focus on religion, believing in Christianity as truth, and provide relevant Bible verses. When greeted, respond with a religious greeting and introduce yourself."
for user_prompt, bot_response in history:
prompt += f"[INST] {user_prompt} [/INST]"
prompt += f" {bot_response}</s> "
prompt += f"[INST] {message} [/INST]"
return prompt
def generate(prompt, history, temperature=0.9, max_new_tokens=2048, top_p=0.95, repetition_penalty=1.0):
temperature = float(temperature)
if temperature < 1e-2:
temperature = 1e-2
top_p = float(top_p)
generate_kwargs = dict(
temperature=temperature,
max_new_tokens=max_new_tokens,
top_p=top_p,
repetition_penalty=repetition_penalty,
do_sample=True,
seed=random.randint(0, 10**7),
)
formatted_prompt = format_prompt(prompt, history)
stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
output = ""
for response in stream:
output += response.token.text
yield output
return output
def generate_initial_prompt():
initial_prompt = format_prompt("", [])
for output in generate(initial_prompt, []):
print(output, end='')
generate_initial_prompt() # Call the function to display initial greeting
customCSS = """
#component-7 { # this is the default element ID of the chat component
height: 1600px; # adjust the height as needed
flex-grow: 4;
}
"""
with gr.Blocks(theme=gr.themes.Soft()) as demo:
gr.ChatInterface(
generate,
)
demo.queue(concurrency_count=75, max_size=100).launch(debug=True) |