| This is the original FP16 result of the model created using chargoddard's frankenllama script so that others interested in further experimentation with the results may do so. | |
| # WARNING: this model is very unpredictable. | |
| This model is an experiment using the frankenstein script from | |
| https://huggingface.co/chargoddard/llama2-22b | |
| Except I decided to use it with two models that have already been extensively finetuned. | |
| With https://huggingface.co/TheBloke/Llama-2-13B-Chat-fp16 as the base model | |
| and | |
| https://huggingface.co/Aeala/Enterredaas-33b as the donor model. | |
| The resulting model is surprisingly coherent and still responds well to the llama2chat prompt format | |
| ```[INST]<<SYS>><</SYS>>[/INST]``` and still has most of llama2chat's bubbly/giddy personality but more gritty and visceral. | |
| It makes occasional "typos" along with some other quirks so it was not completely unscathed by the frankensteining process. | |
| I plan to massage it over with a LoRA in the near future to bring it into more harmony but in the meantime it is available now for your enjoyment. | |
| Use cases: Chat/RP not much else. |