rifkat/GPTuz

<p><b>GPTuzmodel.</b>

GPTuz GPT-2 kichik modelga asoslangan Uzbek tili uchun state-of-the-art til modeli.

Bu model GPU NVIDIA V100 32GB va 0.53 GB malumotlarni kun.uz dan foydalanilgan holda Transfer Learning va Fine-tuning texnikasi asosida 1 kundan ziyod vaqt davomida o'qitilgan.

<p><b>Qanday foydaniladi</b>

<pre><code class="language-python">

from transformers import AutoTokenizer, AutoModelWithLMHead import torch

tokenizer = AutoTokenizer.frompretrained("rifkat/GPTuz") model = AutoModelWithLMHead.frompretrained("rifkat/GPTuz")

tokenizer.modelmaxlength=1024

</code></pre> <p><b>Bitta so'z yaratish</b> <pre><code class="language-python">

text = "Covid-19 га қарши эмлаш бошланди," inputs = tokenizer(text, return_tensors="pt")

outputs = model(**inputs, labels=inputs["inputids"]) loss, logits = outputs[:2] predictedindex = torch.argmax(logits[0, -1, :]).item() predictedtext = tokenizer.decode([predictedindex])

print('input text:', text) print('predicted text:', predicted_text)

</code></pre> <p><b>Bitta to'liq ketma-ketlikni yarating </b>

<pre><code class="language-python">

text = "Covid-19 га қарши эмлаш бошланди, " inputs = tokenizer(text, return_tensors="pt")

sampleoutputs = model.generate(inputs.inputids, padtokenid=50256, dosample=True, maxlength=50, # kerakli token raqamini qo'ying topk=40, numreturn_sequences=1)

for i, sampleoutput in enumerate(sampleoutputs): print(">> Generated text {}\n\n{}".format(i+1, tokenizer.decode(sample_output.tolist())))

</code></pre>

<pre><code class="language-python"> @misc {rifkatdavronov2022, authors = { {Adilova Fatima,Rifkat Davronov, Samariddin Kushmuratov, Ruzmat Safarov} }, title = { GPTuz (Revision 2a7e6c0) }, year = 2022, url = { https://huggingface.co/rifkat/GPTuz }, doi = { 10.57967/hf/0143 }, publisher = { Hugging Face } } </code></pre>