datasets, inference, license, language, pipeline_tag, widget, library_name, tags

datasets	inference	license	language	pipeline_tag	widget	library_name	tags
IlyaGusev/habr Den4ikAI/russian_instructions wiki_qa	parameters max_new_tokens temperature top_k top_p do_sample 32 1 50 0.7 true	apache-2.0	en	text-generation	text example_title Чем отличается лось от ежа? Question Answering text example_title Как выпросить повышение? Logical reasoning text example_title Какая температура закипания азота? Scientific knowledge	transformers	finance code

Instructions ruGPT Small v0.1a

Model Summary

Я дообучил small rugpt на датасете инструкций, хабра, QA и кода

Quick Start

from transformers import pipeline
pipe = pipeline(model='AlexWortega/instruct_rugptSmall')
pipe('''Как собрать питон код?''')

or

from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("AlexWortega/instruct_rugptSmall")
model = AutoModelForCausalLM.from_pretrained("AlexWortega/instruct_rugptSmall")

License

The weights of Instructions ruGPT Small v0.1a are licensed under version 2.0 of the Apache License.

Hyperparameters

I used Novograd with a learning rate of 2e-5 and global batch size of 6 (3 for each data parallel worker). I use both data parallelism and pipeline parallelism to conduct training. During training, we truncate the input sequence to 1024 tokens, and for input sequence that contains less than 1024 tokens, we concatenate multiple sequences into one long sequence to improve the data efficiency.

References

#Metrics

SOON

BibTeX entry and citation info

@article{
  title={GPT2xl is underrated task solver},
  author={Nickolich Aleksandr, Karina Romanova, Arseniy Shahmatov, Maksim Gersimenko},
  year={2023}
}