File size: 1,479 Bytes
0a58748 9101334 0a58748 9101334 0a58748 9101334 0a58748 2188ac0 0a58748 |
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 |
import gradio as gr
import os
from transformers import pipeline, set_seed
from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0]
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')
model = AutoModel.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')
def Bemenet(input_string):
# Tokenize sentences
encoded_input = tokenizer([input_string], padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
# Normalize embeddings
return F.normalize(sentence_embeddings, p=2, dim=1)
interface = gr.Interface(fn=Bemenet,
title="Beágyazások",
description="Az itt megosztott példa mondatokhoz készít beágyazásokat (embedding). A bal oldali input mezőbe beírt mondat beágyazása a jobb oldali szöveges mezőben jelenik meg.",
inputs="text",
outputs="text")
interface.launch() |