| --- |
| license: apache-2.0 |
| language: |
| - en |
| pipeline_tag: text-generation |
| widget: |
| - text: 10 Meditation tips |
| example_title: Health Exmaple |
| - text: Cooking red sauce pasta |
| example_title: Cooking Example |
| - text: Introduction to Keras |
| example_title: Technology Example |
| tags: |
| - text-generation |
| --- |
| # ScriptGPT-small |
|
|
| ## 🖊️ Model description |
| ScriptGPT-small is a language model trained on a dataset of 100 YouTube videos that cover different domains of Youtube videos. |
| ScriptGPT-small is a Causal language transformer. The model resembles the GPT2 architecture, the model is a Causal Language model meaning it predicts the probability of a sequence of words based on the preceding words in the sequence. |
| It generates a probability distribution over the next word given the previous words, without incorporating future words. |
|
|
| The goal of ScriptGPT-small is to generate scripts for Youtube videos that are coherent, informative, and engaging. |
| This can be useful for content creators who are looking for inspiration or who want to automate the process of generating video scripts. |
| To use ScriptGPT-small, users can provide a prompt or a starting sentence, and the model will generate a sequence of words that follow the context and style of the training data. |
|
|
| Models |
| - [Script_GPT](https://huggingface.co/SRDdev/Script_GPT) : AI content Model |
| - [ScriptGPT-small](https://huggingface.co/SRDdev/ScriptGPT-small) : Generalized Content Model |
|
|
| More models are coming soon... |
|
|
| ## 🛒 Intended uses |
| The intended uses of ScriptGPT-small include generating scripts for videos, providing inspiration for content creators, and automating the process of generating video scripts. |
|
|
|
|
| ## 📝 How to use |
| You can use this model directly with a pipeline for text generation. |
|
|
| 1. __Load Model__ |
| ```python |
| from transformers import AutoTokenizer, AutoModelForCausalLM |
| |
| tokenizer = AutoTokenizer.from_pretrained("SRDdev/ScriptGPT-small") |
| model = AutoModelForCausalLM.from_pretrained("SRDdev/ScriptGPT-small") |
| ``` |
|
|
| 2. __Pipeline__ |
| ```python |
| from transformers import pipeline |
| generator = pipeline('text generation, model= model , tokenizer=tokenizer) |
| |
| context = "Cooking red sauce pasta" |
| length_to_generate = 250 |
| |
| script = generator(context, max_length=length_to_generate, do_sample=True)[0]['generated_text'] |
| |
| script |
| ``` |
| <p style="opacity: 0.8">The model may generate random information as it is still in beta version</p> |
|
|
| ## 🎈Limitations and bias |
| > The model is trained on Youtube Scripts and will work better for that. It may also generate random information and users should be aware of that and cross-validate the results. |
|
|
| ## Citations |
| ``` |
| @model{ |
| Name=Shreyas Dixit |
| framework=Pytorch |
| Year=Jan 2023 |
| Pipeline=text-generation |
| Github=https://github.com/SRDdev |
| LinkedIn=https://www.linkedin.com/in/srddev |
| } |
