SCI FI STORY WITH CAVORITE CODE
In the code snippet above, we specify the model’s arguments ( ModelArguments), data arguments ( DataTrainingArguments), and training arguments ( TrainingArguments). Note: I took the code from this transformers example file and modified it. We need torch because it is used for training. We need the transformers library to load the pre-trained GPT-2 checkpoint and fine-tune it.
SCI FI STORY WITH CAVORITE INSTALL
!pip install transformers torchĪbove, we are installing the core libraries. I will go through some of the core code from the Colab notebook in this post.
Here’s the 6_genre_clean_training_data.txt (training file) and 6_genre_eval_data.txt (evaluation file) that you need to upload to your Colab notebook’s environment before running the code. You can create a copy of this notebook and modify it for your own dataset as well. The link to the colab notebook for fine-tuning our model is here. I recommend that you train the model on Google Colab (Set runtime to GPU). The subjects: physics, chemistry, computer_science, etc. To create your own dataset for another task, like generating research paper abstracts based on subjects, each example’s format can be similar like this: The genres: superhero, sci_fi, horror, action, drama, thriller Each line in the file is a story of this format: The training file has over 30,000 stories.
SCI FI STORY WITH CAVORITE MOVIE
It does all the heavy-lifting for us.įor this idea, I created the dataset files by cleaning, transforming and combining the Kaggle Wikipedia Movie Plots dataset along with scraped superhero comic book plots from Wikipedia. To fine-tune and use the GPT-2 pre-trained model, we will use the huggingface/transformers library. We can fine-tune (further train) pre-trained models like GPT-2 on a chosen dataset to tailor their performance towards that dataset. It was pre-trained ( with 40GB of text data) on the task of predicting the next word (more formally, token) at each time-step given preceding text as input.If this seems like mumbo-jumbo, just know that Transformer is a state-of-the-art architecture for NLP models. GPT-2 is a text-generation language model using a Decoder-only Transformer (a variant of Transformers architecture).If you’re looking for a detailed overview of GPT-2, you can get it straight from the horse’s mouth.īut, If you just want a quick summary of GPT-2, here’s a distilled rundown: So, we can use it on many devices (including iPhones). While still bulky, GPT-2 takes up much less space (largest variant takes up 6GB disk space). Just like its hype, GPT-3’s size is also gigantic ( rumored to require 350 GB of RAM). Wait, why are we using GPT-2 and not GPT-3? Well, it’s in Beta. Recently, we saw the humongous hype behind text-generation model GPT-3 and its dazzling performance for tasks like generating code using zero-shot learning. Otherwise, get a quick refresher on GPT-2 below. This process is experimental and the keywords may be updated as the learning algorithm improves.If you’re familiar with the key ideas of GPT-2, you can fast-forward to the next act. These keywords were added by machine and not by the authors. It is these elements, combined with an assured narrative style, which have won for The First Men in the Moon a permanent place in the literature of science fiction as a classic of the imagination. What is new and original in Wells’s story is first the fact that the journey to the moon is undertaken not by caricature figures but by well-drawn and convincing individuals second, the idea of the anti-gravity device, ‘Cavorite’, which makes possible the construction of the sphere third, the detailed and circumstantial descriptions of the lunar landscape and finally the satirical account of the Selenite civilisation. And ih 1865 Jules Verne returned to the theme in From the Earth to the Moon (and again in a sequel, Round the Moon). In 1835 Edgar Allan Poe, in The Unparalleled Adventure of One Hans Pfaall, gave an account of a flight to the moon and back in a balloon.
As long ago as the second century Lucian in Icaromenippus had exploited the idea, and a quotation from his romance appears on the title page of the first edition. The idea of describing an imaginary journey to the moon had been attempted by many writers before The First Men in the Moon appeared in 1901.
0 kommentar(er)
