metadata
language:
- en
tags:
- ggml
- causal-lm
- gpt2
license: mit
▄▄▄ ██▓ ▓█████▄ █ ██ ███▄ █ ▄████ ▓█████ ▒█████ ███▄ █
▒████▄ ▓██▒ ▒██▀ ██▌ ██ ▓██▒ ██ ▀█ █ ██▒ ▀█▒▓█ ▀ ▒██▒ ██▒ ██ ▀█ █
▒██ ▀█▄ ▒██▒ ░██ █▌▓██ ▒██░▓██ ▀█ ██▒▒██░▄▄▄░▒███ ▒██░ ██▒▓██ ▀█ ██▒
░██▄▄▄▄██ ░██░ ░▓█▄ ▌▓▓█ ░██░▓██▒ ▐▌██▒░▓█ ██▓▒▓█ ▄ ▒██ ██░▓██▒ ▐▌██▒
▓█ ▓██▒░██░ ░▒████▓ ▒▒█████▓ ▒██░ ▓██░░▒▓███▀▒░▒████▒░ ████▓▒░▒██░ ▓██░
▒▒ ▓▒█░░▓ ▒▒▓ ▒ ░▒▓▒ ▒ ▒ ░ ▒░ ▒ ▒ ░▒ ▒ ░░ ▒░ ░░ ▒░▒░▒░ ░ ▒░ ▒ ▒
▒ ▒▒ ░ ▒ ░ ░ ▒ ▒ ░░▒░ ░ ░ ░ ░░ ░ ▒░ ░ ░ ░ ░ ░ ░ ▒ ▒░ ░ ░░ ░ ▒░
░ ▒ ▒ ░ ░ ░ ░ ░░░ ░ ░ ░ ░ ░ ░ ░ ░ ░ ░ ░ ░ ▒ ░ ░ ░
░ ░ ░ ░ ░ ░ ░ ░ ░ ░ ░ ░
This repository contains quantized conversions of the AI Dungeon 2 checkpoint, "model_v5".
For use with frontends that support GGML quantized GPT-2 models.
Last updated on 2023-09-23.
| Model | RAM usage (KoboldCpp) | RAM usage (Oobabooga) |
|---|---|---|
| aid2classic-ggml-q4_0.bin | 984.1 MiB | 1.4 GiB |
| aid2classic-ggml-q4_1.bin | 1.1 GiB | 1.5 GiB |
| aid2classic-ggml-q5_0.bin | 1.2 GiB | 1.6 GiB |
| aid2classic-ggml-q5_1.bin | 1.2 GiB | 1.7 GiB |
| aid2classic-ggml-q8_0.bin | 1.7 GiB | 2.2 GiB |
| aid2classic-ggml-f16.bin | 3.2 GiB | 3.6 GiB |
Description:
2019 AI Dungeon users may recognize the model quantized was used by the open-source AI Dungeon 2 project and its various forks. This was before it moved to its own website and rebranded to "AI Dungeon".
2020-2021 AI Dungeon users may recognize this model as "Classic".
If you want a better model trained on the same dataset, see Spring Dragon 13B, intended to replicate 2020 AI Dungeon's "Dragon" experience on local hardware.
Notes:
- KoboldCpp [bfc696f] was tested without OpenBLAS.
- Oobabooga [895ec9d] was tested with with the
--model <model> --loader ctransformers --model_type gpt2launch arguments. - ggerganov/ggml [8ca2c19]'s gpt-2 conversion script was used for conversion and quantization.
- The original model was found in the
generator/gpt2/models/model_v5directory of AI Dungeon 2 Unleashed.