92 lines
3.3 KiB
Markdown
92 lines
3.3 KiB
Markdown
---
|
|
license: cc-by-nc-4.0
|
|
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
---
|
|
|
|
# Disclaimer:
|
|
## This model is experimental, do not expect everything to work.
|
|
|
|
This model uses the Alpaca **prompting format**(or just directly download the SillyTavern instruct preset [here](https://files.catbox.moe/0ohmco.json))
|
|
|
|
---
|
|
|
|
|
|
Beeg noromaid on ***steroids***. Suitable for RP, ERP.
|
|
|
|
This time based on Mixtral Instruct, seems to do wonders!
|
|
|
|
This model was trained for 8h(v1) + 8h(v2) + 12h(v3) on customized modified datasets, focusing on RP, uncensoring, and a modified version of the Alpaca prompting (that was already used in LimaRP), which should be at the same conversational level as ChatLM or Llama2-Chat without adding any additional special tokens.
|
|
|
|
If you wanna have more infos about this model(and v1 + v2) you can check out [my blog post](https://ikaridevgit.github.io/index.html?p=7&blog=blogid-6&bo=true)
|
|
|
|
[Recommended settings - Settings 1](https://huggingface.co/NeverSleep/Noromaid-v0.1-mixtral-8x7b-v3/discussions/1)
|
|
|
|
[Recommended settings - Settings 2 (idk if they are any good)](https://files.catbox.moe/fv4xhu.json)
|
|
|
|
## Credits:
|
|
- Undi
|
|
- IkariDev
|
|
|
|
<!-- description start -->
|
|
## Description
|
|
|
|
<!-- [Recommended settings - contributed by localfultonextractor](https://files.catbox.moe/ue0tja.json) -->
|
|
|
|
This repo contains FP16 files of Noromaid-v0.1-mixtral-8x7b-Instruct-v3.
|
|
|
|
[FP16 - by IkariDev and Undi](https://huggingface.co/NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3)
|
|
|
|
<!-- [GGUF - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GGUF)-->
|
|
|
|
<!-- [GPTQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GPTQ)-->
|
|
|
|
<!-- [exl2[8bpw-8h] - by AzureBlack](https://huggingface.co/AzureBlack/Echidna-13b-v0.3-8bpw-8h-exl2)-->
|
|
|
|
<!-- [AWQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-AWQ)-->
|
|
|
|
<!-- [fp16 - by IkariDev+Undi95](https://huggingface.co/IkariDev/Athena-v4)-->
|
|
|
|
[GGUF - by IkariDev and Undi](https://huggingface.co/NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3-GGUF)
|
|
<!-- [OLD(GGUF - by IkariDev+Undi95)](https://huggingface.co/IkariDev/Athena-v4-GGUF)-->
|
|
|
|
## Ratings:
|
|
|
|
Note: We have permission of all users to upload their ratings, we DONT screenshot random reviews without asking if we can put them here!
|
|
|
|
No ratings yet!
|
|
|
|
If you want your rating to be here, send us a message over on DC and we'll put up a screenshot of it here. DC name is "ikaridev" and "undi".
|
|
|
|
<!-- description end -->
|
|
<!-- prompt-template start -->
|
|
### Custom format:
|
|
```
|
|
### Instruction:
|
|
{system prompt}
|
|
|
|
### Input:
|
|
{input}
|
|
|
|
### Response:
|
|
{reply}
|
|
```
|
|
|
|
## Datasets used:
|
|
|
|
- Aesir 1 and 2 ([MinervaAI](https://huggingface.co/MinervaAI) / [Gryphe](https://huggingface.co/Gryphe))
|
|
- [LimaRP-20231109](https://huggingface.co/datasets/lemonilia/LimaRP) ([Lemonilia](https://huggingface.co/lemonilia))
|
|
- [ToxicDPO-NoWarning](https://huggingface.co/datasets/Undi95/toxic-dpo-v0.1-sharegpt) ([unalignment orga repo](https://huggingface.co/unalignment) + [Undi](https://huggingface.co/Undi95))
|
|
- [No-robots-ShareGPT](https://huggingface.co/datasets/Doctor-Shotgun/no-robots-sharegpt) ([Doctor-Shotgun](https://huggingface.co/Doctor-Shotgu))
|
|
|
|
|
|
## Others
|
|
|
|
Undi: If you want to support me, you can [here](https://ko-fi.com/undiai).
|
|
|
|
IkariDev: Visit my [retro/neocities style website](https://ikaridevgit.github.io/) please kek |