license: apache-2.0
datasets:
- SRDdev/Youtube-Scripts
language:
- en
pipeline_tag: text-generation
widget:
- text: Introduction to Vertex AI Feature Store
example_title: Example 1
- text: Introduction to JAX
exmaple_title: Example 2
tags:
- Text-Generation
- Scripts
Script_GPT
Model Details
The Script_GPT is a language model developed using the Hugging Face Transformers library. It is trained on a custom dataset of YouTube scripts and can be used to generate new scripts for YouTube videos. The model is based on the GPT architecture and has a total of 117M parameters.
Intended Use
The Script_GPT model is intended to be used for generating scripts for YouTube videos. It can be used by content creators, marketers, and other individuals who want to produce high-quality scripts for their YouTube channels.
Limitations and Bias
The Script_GPT model is trained on a custom dataset of YouTube scripts, which may not represent all possible types of videos on the platform. As a result, the model may have limitations when generating scripts for certain types of videos. Additionally, like all language models, the Script_GPT model may exhibit bias in its outputs based on the biases present in the training data. It is important to review and evaluate the model's outputs to ensure that they are free from bias and harmful content.
Training Data
The Script_GPT model was trained on a custom dataset of YouTube scripts, which was collected from a variety of sources, including popular YouTube channels and public scripts available online. The dataset consists of only 6 scripts. The scripts are biased towards the Youtuber Ali Abdala.
How to Use
Installation To use the Script_GPT model, you first need to install the Hugging Face Transformers library:
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("SRDdev/Script_GPT")
model = AutoModelForCausalLM.from_pretrained("SRDdev/Script_GPT")
Generating Scripts To generate scripts using the Script_GPT model, you can use the following code:
from transformers import pipeline
generator = pipeline('text-generation', model="SRDdev/Script_GPT",tokenizer="SRDdev/Script_GPT")
text = generator("Write a Script on Deep Learning ", max_length=1000, do_sample=True)[0]['generated_text']
print(text)