Spaces:
Sleeping
Sleeping
File size: 1,662 Bytes
a070f41 e905207 4de15a4 a070f41 4de15a4 f090db9 a070f41 4de15a4 a070f41 f090db9 4de15a4 f090db9 4de15a4 f090db9 4de15a4 |
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 |
from huggingface_hub import InferenceClient
import gradio as gr
import torch
# Sprawdź, czy CUDA jest dostępne
device = "cuda" if torch.cuda.is_available() else "cpu"
client = InferenceClient("mistralai/Mixtral-8x7B-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, max_new_tokens=3500, 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=42,
device=device, # Dodajemy obsługę CUDA
)
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
mychatbot = gr.Chatbot(
bubble_full_width=False, show_label=False, show_copy_button=True, likeable=True,)
demo = gr.ChatInterface(fn=generate,
chatbot=mychatbot,
title="Test API :)",
retry_btn=None,
undo_btn=None
)
demo.queue().launch(show_api=True)
|