Undi95/Dawn-v2-70B-2.55bpw-h6-exl2 - Каталог нейросетей
Генерация текста

Undi95/Dawn-v2-70B-2.55bpw-h6-exl2

Добавлено:

This repo contains exl2 (2.55bpw, h6) files of Dawn-70B, a merge I have done with the new layer shuffle method from mergekit. 2.55bpw seems a little hard to make working, but it can be sorted out, just try to find good setting. Other quant available here thanks to AzureBlack, also, a big thanks to TheBloke for the compute power that let me test different GPU for the EXL2 quant. Don’t use this. THIS WILL break it up 100% at low bpw. !image/png Also, you need to disable Added BOS token, it will break it too. !image/png UtopiaXL was a huge success for me, I really liked it, so I took the same path to do this 70B: A good base, some psychologic data, some medical data, a little bit of this, of that, and LimaRP at the end as always. — Sao10K/Euryale-1.3-L2-70B — Xwin-LM/Xwin-LM-70B-V0.1 — ehartford/Samantha-1.11-70b — NousResearch/Nous-Hermes-Llama2-70b — augtoma/qCammel-70-x — jondurbin/airoboros-l2-c70b-3.1.2 — fangloveskari/ORCALLaMA70B_QLoRA — Doctor-Shotgun/limarpv3-llama2-70b-qlora A big thanks to Charles for adding the layer shuffle method to his tool mergekit and Henky/KoboldAI for the machine he let me use.

Модальности:
Генерация текста


Задача: Генерация текста
Автор: Undi95
Теги: llama, not-for-all-audiences, nsfw, text-generation-inference, endpoints_compatible
Лайков: 2  |  Загрузок: 6

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.