--- tags: - not-for-all-audiences --- # EXL2 quants of [crestf411/llama-3-daybreak-storywriter-v0.2-70b-hf](https://huggingface.co/crestf411/llama-3-daybreak-storywriter-v0.2-70b-hf) [2.50 bits per weight](https://huggingface.co/kim512/llama-3-daybreak-storywriter-v0.2-70b-hf-2.5bpw-exl2) [3.00 bits per weight](https://huggingface.co/kim512/llama-3-daybreak-storywriter-v0.2-70b-hf-3.0bpw-exl2) [3.50 bits per weight](https://huggingface.co/kim512/llama-3-daybreak-storywriter-v0.2-70b-hf-3.5bpw-exl2) [4.00 bits per weight](https://huggingface.co/kim512/llama-3-daybreak-storywriter-v0.2-70b-hf-4.0bpw-exl2) [4.50 bits per weight](https://huggingface.co/kim512/llama-3-daybreak-storywriter-v0.2-70b-hf-4.5bpw-exl2) [5.00 bits per weight](https://huggingface.co/kim512/llama-3-daybreak-storywriter-v0.2-70b-hf-5.0bpw-exl2) [6.00 bits per weight](https://huggingface.co/kim512/llama-3-daybreak-storywriter-v0.2-70b-hf-6.0bpw-exl2) [8.00 bits per weight](https://huggingface.co/kim512/llama-3-daybreak-storywriter-v0.2-70b-hf-8.0bpw-exl2) Note: 2.0bpw produces a quant that does not work. # Daybreak (2024 May) v0.2 LoRA on top of https://huggingface.co/tdrussell/Llama-3-70B-Instruct-Storywriter The venerable [mradermacher](https://huggingface.co/mradermacher) has made GGUF quants available: [GGUF](https://huggingface.co/mradermacher/llama-3-daybreak-storywriter-v0.2-70b-hf-GGUF/tree/main), [i1-GGUF](https://huggingface.co/mradermacher/llama-3-daybreak-storywriter-v0.2-70b-hf-i1-GGUF/tree/main) Beware, depraved. Not suitable for any audience. Starting point (random anon recommendation): * Typical P 0.98 * Min P 0.05 * Smoothing 0.24 * Dynamic temp 0.4 low 2.95 high The LoRA is slop-free (but the base model is not, so complete elimination is very hard). The below regexes return 0 matches. * 'barely above a whisper', * 'shiver([s]?) down', * ' ministration', * 'audible (["\'"]?)p[l]?op', * 'buck([s]?) my ', * 'buck([s]?) h[ei][rs] ', * '[Dd]espite h[ie][mr]self', * 'slick slit', * 'whatever it takes', If there are other phrases, please let me know. Also please let me know if there are phrases that this or other daybreak models use repeatedly/too often. I continuously update the dataset.