DanTagGen alpha DanTagGen(Danbooru Tag Generator) is inspired from p1atdev's dart project. But with different arch, dataset, format and different training strategy. Model arch This version of DTG is trained from scratch with 400M param LLaMA arch.(In my personal preference I will call it NanoLLaMA) Since it is llama arch. Theoritically it should be able to be used in any LLaMA inference interface. This repo also provided converted FP16 gguf model and quantized 8bit/6bit gguf models. Basically it is recommended to use llama.cpp or llama cpp python to run this model. Which will be very fast. Format for example: And you may get something like: Dataset and Training I use the trainer I implemented in HakuPhi to run the training. (It should be HakuLLM now LoL) with 15epoch on 2M data and 5epoch on 5.3M data. This model have roughly 6~12B token seen. The dataset is exported by HakuBooru with my danbooru sqlite database. Use the percentile of fav count on each rating to filter the data. (2M = top 25%, 5.3M = top 75%) Utilities I'm implementing a gradio UI for this thing and other dev can utilize the API in it to make different app. I'm also planning to make sd webui extension.
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy