113 lines
3.4 KiB
Markdown
113 lines
3.4 KiB
Markdown
---
|
||
datasets:
|
||
- IlyaGusev/habr
|
||
- Den4ikAI/russian_instructions
|
||
- wiki_qa
|
||
inference:
|
||
parameters:
|
||
min_length: 20
|
||
max_new_tokens: 100
|
||
top_k: 50
|
||
top_p: 0.9
|
||
early_stopping: True
|
||
no_repeat_ngram_size: 2
|
||
use_cache: True
|
||
repetition_penalty: 1.5
|
||
length_penalty: 0.8
|
||
num_beams: 4
|
||
|
||
license: apache-2.0
|
||
language:
|
||
- ru
|
||
pipeline_tag: text-generation
|
||
widget:
|
||
- text: "Может ли встретиться пингвин и белый медведь?"
|
||
example_title: Question Answering
|
||
- text: "Как зарабатывать много денег обучая модели?"
|
||
example_title: Open domain Knoweledge
|
||
- text: "Напиши код который выведет Привет Мир"
|
||
example_title: Scientific knowledge
|
||
library_name: transformers
|
||
tags:
|
||
- finance
|
||
- code
|
||
---
|
||
|
||
<h1 style="font-size: 42px">Instructions ruGPT Medium v0.11_75к_a<h1/>
|
||
|
||
|
||
|
||
# Model Summary
|
||
|
||
> Это ruGPTMedium дообученная в инструктивно-флановом сетапе, она более ли менее ZSшотиться и FSшотиться и работает лучше чем XGLM1.7b, mgpt на русском языке
|
||
|
||
|
||
# Quick Start
|
||
|
||
```python
|
||
from transformers import pipeline
|
||
#в душе не ебу будет ли норм работать, ставлю жопу автора хф что токенайзер мисматчнет с моделью, вообще грузите по нормальному
|
||
pipe = pipeline(model='AlexWortega/instruct_rugptMedium')
|
||
pipe('''Как собрать питон код?''')
|
||
```
|
||
or
|
||
```python
|
||
from transformers import GPT2TokenizerFast,GPT2LMHeadModel
|
||
tokenizer = GPT2TokenizerFast.from_pretrained("AlexWortega/instruct_rugptMedium")
|
||
special_tokens_dict = {'additional_special_tokens': ['<code>', '</code>', '<instructionS>', '<instructionE>', '<next>']}
|
||
|
||
tokenizer.add_special_tokens(special_tokens_dict)
|
||
device = 'cuda:1'
|
||
model = GPT2LMHeadModel.from_pretrained("AlexWortega/instruct_rugptMedium")
|
||
model.to(device)
|
||
|
||
model.resize_token_embeddings(len(tokenizer))
|
||
```
|
||
обратите внимание, что лучшие параметры для генерации
|
||
```
|
||
gen_kwargs = {
|
||
"min_length": 20,
|
||
"max_new_tokens": 100,
|
||
"top_k": 50,
|
||
"top_p": 0.9,
|
||
"do_sample": True,
|
||
"early_stopping": True,
|
||
"no_repeat_ngram_size": 2,
|
||
"eos_token_id": tokenizer.eos_token_id,
|
||
"pad_token_id": tokenizer.eos_token_id,
|
||
"use_cache": True,
|
||
"repetition_penalty": 1.5,
|
||
"length_penalty": 0.8,
|
||
"num_beams": 4,
|
||
"num_return_sequences": k
|
||
}
|
||
```
|
||
# 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
|
||
|
||
```bibtex
|
||
@article{
|
||
title={GPT2xl is underrated task solver},
|
||
author={Nickolich Aleksandr, 5Q, datascience, Ilya Gusev, Alex Kukushkin, Karina Romanova, Arseniy Shahmatov, Maksim Gersimenko},
|
||
year={2023}
|
||
}
|
||
``` |