metadata
language:
- en
- he
base_model:
- openai-community/gpt2
pipeline_tag: text-generation
library_name: transformers
To use this model, please input a style like this:
user1: [message]\nuser2:
user1 is the input, and the output will be generated by user2. Messages are allowed for context before, but it's recommended that they follow that format. Numbers next to the user don't matter.
This model is GPT2 fine-tuned with 1.5M Tokens of a diverse custom discord dataset.
It will be updated as training improves. Currently, it's 100% unsupervised learning.
Current Version: 0.5
28% done with Unsupervised Fine-tuning