README.md

metadata

language:
  - en
tags:
  - ggml
  - causal-lm
  - gpt2
  - text-generation
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. This model works best with KoboldCpp's "Adventure" mode.

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 this model as the same one that powered the open-source AI Dungeon 2 project and its various forks. This was before AI Dungeon 2 moved to its own website and consequently rebranded to "AI Dungeon".
• 2020-2021 AI Dungeon users may recognize this model as "Classic", the free tier below Griffin (free, but later used "energy") and Dragon (subscription).
• If you want a better model trained on the same dataset at the cost of higher hardware requirements, check out Spring Dragon 13B, intended to replicate 2020 AI Dungeon's "Dragon" experience on local hardware.
• The motivation behind these quantizations was that Henk717/ai-dungeon2-classic-ggml was older and lacked other quantization formats. The workflow for this quantization was also different: henk717's mentions being converted to a 16-bit Pytorch checkpoint before being converted to GGML. This one was converted straight from Tensorflow to 16-bit GGML before being quantized.

Notes:

• KoboldCpp [bfc696f] was tested without OpenBLAS.
• Oobabooga [895ec9d] was tested with with the --model <model> --loader ctransformers --model_type gpt2 launch 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_v5 directory of AI Dungeon 2 Unleashed.