Spaces:
Sleeping
Sleeping
File size: 1,585 Bytes
5c0e14a 08eb742 5c0e14a d9ab650 5c0e14a 08eb742 5c0e14a 17fba42 08eb742 5c0e14a 08eb742 5c0e14a 08eb742 |
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 |
from huggingface_hub import InferenceClient
import gradio as gr
client = InferenceClient(
"mistralai/Mistral-7B-Instruct-v0.1"
)
def format_prompt(message, history):
prompt = "<s>"
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=2000, top_p=0.9, repetition_penalty=1.2,
):
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=42,
)
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
css = """
#mkd {
height: 500px;
overflow: auto;
border: 1px solid #ccc;
}
"""
with gr.Blocks(css=css) as demo:
gr.HTML("<h1><center><h1><center>")
gr.HTML("<h3><center><h3><center>")
gr.HTML("<h3><center><h3><center>")
gr.ChatInterface(
generate,
examples=[["What is the secret to life?"], ["Write me a recipe for pancakes."], ["Write a short story about Paris."]]
)
demo.launch(debug=True)
|