ReMM-v2-L2-13B-GGUF / README.md
llama-anon's picture
Update README.md
9aa3db5
|
raw
history blame
1.44 kB
---
license: cc-by-nc-sa-4.0
---
Brouz was here first. (he said)
Re:MythoMax v2 (ReMM v2) is a recreation trial of the original [MythoMax-L2-B13](https://huggingface.co./Gryphe/MythoMax-L2-13b) with updated models.
This merge use SLERP merging method to merge ReML v2 and Huginn v1.2.
Explaination :
```shell
- ReML-v2: (Chronos-Beluga v2/Hermes/Airboros 2.1)
=> Keeping The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16
=> Replacing jondurbin/airoboros-l2-13b-2.1 by jondurbin/spicyboros-13b-2.2 (last version)
=> Keeping NousResearch/Nous-Hermes-Llama2-13b
With that :
- ReMM-v2: (ReML/Huginn v1.2)
=> Replacing ReMM by the one above (ReML v2)
=> Keeping The-Face-Of-Goonery/Huginn-13b-v1.2 (hottest)
```
<!-- description start -->
## Description
This repo contains quantized files of ReMM v2, a recreation of the original MythoMax, but updated and merged with SLERP.
<!-- description end -->
<!-- description start -->
## Models used
- The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16
- jondurbin/spicyboros-13b-2.2
- NousResearch/Nous-Hermes-Llama2-13b
- The-Face-Of-Goonery/Huginn-13b-v1.2
- ReML-v2-L2-13B (Private recreation trial of an updated Mythologic-L2-13B)
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
Special thanks to Sushi kek