|
|
--- |
|
|
license: mit |
|
|
language: |
|
|
- en |
|
|
tags: |
|
|
- text-generation-inference |
|
|
pipeline_tag: text-generation |
|
|
--- |
|
|
|
|
|
## GPT-First Person Experience |
|
|
An 6.83-million parameter LLM using GPT-2 encodings. |
|
|
Trained using 80MB of text adventure game transcripts. |
|
|
|
|
|
Use this to provide another GPT model with a first-person experience. |
|
|
|
|
|
Supervised fine-tuning should be performed before use. |
|
|
|
|
|
## Technical Information |
|
|
| | | |
|
|
|---------------------------------|----:| |
|
|
|Layers |2| |
|
|
|Heads |2| |
|
|
|Embeddings |128| |
|
|
|Context Window |16384 tokens| |
|
|
|Tokenizer |GPT-2 BPE| |
