| license: other | |
| Continuation of https://huggingface.co/nkpz/llama2-22b-daydreamer-v1 | |
| Trained it a couple more epochs on airoboros v2 general data. | |
| This resulted in improvements to its obsession with overexplaining itself - it's a little less instruction focused and feels more versatile. Still needs work overall, but I think it's moving in the right direction. | |
| Still more to come. Going to try to find a way to improve its problem solving skills without ruining the output style. |