SRDdev/ScriptForge

1---2license: apache-2.03datasets:4- SRDdev/Youtube-Scripts5language:6- en7pipeline_tag: text-generation8widget:9- text: Introduction to Keras ?10  example_title: Example 111- text: Introduction to Vertex AI Feature Store12  exmaple_title: Example 213tags:14- Text-Generation15---16 17# ScriptForge18 19 20## 🖊️ Model description 21ScriptForge is a language model trained on a dataset of 5,000 YouTube videos that explain artificial intelligence (AI) concepts.22ScriptForge is a Causal language transformer. The model resembles the GPT2 architecture, 23the model is a Causal Language model meaning it predicts the probability of a sequence of words based on the preceding words in the sequence. 24It generates a probability distribution over the next word given the previous words, without incorporating future words.25 26The goal of ScriptForge is to generate scripts for AI videos that are coherent, informative, and engaging. 27This can be useful for content creators who are looking for inspiration or who want to automate the process of generating video scripts. 28To use ScriptGPT, 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.29 30Models31- [ScriptForge](https://huggingface.co/SRDdev/Script_GPT)      : AI content Model32- [ScriptForge-small](https://huggingface.co/SRDdev/ScriptGPT-small) : Generalized Content Model33 34More models are coming soon...35 36## 🛒 Intended uses37The intended uses of ScriptForge include generating scripts for videos that explain artificial intelligence concepts, providing inspiration for content creators, and 38automating the process of generating video scripts. 39 40 41## 📝 How to use42You can use this model directly with a pipeline for text generation.43 441. __Load Model__45```python46from transformers import AutoTokenizer, AutoModelForCausalLM47 48tokenizer = AutoTokenizer.from_pretrained("SRDdev/ScriptForge")49model = AutoModelForCausalLM.from_pretrained("SRDdev/ScriptForge")50```51 522. __Pipeline__53```python54from transformers import pipeline55generator = pipeline('text-generation', model= model , tokenizer=tokenizer)56 57context = "Introduction to Vertex AI Feature Store"58length_to_generate = 200 59 60script = generator(context, max_length=length_to_generate, do_sample=True)[0]['generated_text']61```62<p style="opacity: 0.8">Keeping the context more technical and related to AI will generate better outputs</p>63 64## 🎈Limitations and bias65> 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.66 67The used is linked [here](https://www.kaggle.com/datasets/jfcaro/5000-transcripts-of-youtube-ai-related-videos)68 69## Citations70```71@model{72        Name=Shreyas Dixit73        framework=Pytorch74        Year=Jan 202375        Pipeline=text-generation76        Github=https://github.com/SRDdev77        LinkedIn=https://www.linkedin.com/in/srddev78      }79```