|
--- |
|
license: llama2 |
|
--- |
|
--- |
|
license: llama2 |
|
--- |
|
This is the GGML version of LaMA 2 Holomax 13B for use with [Koboldcpp](https://koboldai.org/cpp) for the original HF compatible release please check [KoboldAI/LLaMA2-13B-Holomax](https://huggingface.co/KoboldAI/LLaMA2-13B-Holomax) |
|
|
|
# LLaMA 2 Holomax 13B - The writers version of Mythomax |
|
|
|
This is an expansion merge to the well praised Mythomax model from Gryphe (60%) using MrSeeker's KoboldAI Holodeck model (40%) |
|
The goal of this model is to enhance story writing capabilities while preserving the desirable traits of the Mythomax model. |
|
|
|
Testers found that this model passes the InteracTV benchmark, was useful for story writing, chatting and text adventures using Instruction mode. |
|
Preservation of factual knowledge has not been tested since we expect the original to be better in those use cases as this merge was focussed on fiction. |
|
|
|
## Credits |
|
This merge is not possible without the following models and model authors (Thanks to all of you for your work!) |
|
|
|
Mythomax by Gryphe: |
|
- Mythologic-L2 by Gryphe: |
|
- - Hermes by Nous-Research |
|
- Chronos V2 by Elinas |
|
- Airoboros m2.0 by Jondurbin |
|
- Huginn by Face of Goonery: |
|
- - Hermes by Nous-Research |
|
- StableBeluga by StabilityAI |
|
- Airoboros by Jondurbin |
|
- Chronos by Elinas |
|
- Limarp by Lemonila |
|
|
|
Holodeck by Mr.Seeker |
|
|
|
## Guidelines |
|
This model is designed to be flexible, it should be able to be used as a co-writing model, as well as a variety of instruct formats (Tested with Alpaca) and regular chatting both augmented with traditional formatting and instruct formatting. |
|
The Alpaca format is as follows: |
|
``` |
|
### Instruction: |
|
|
|
Instruction goes here |
|
|
|
### Response: |
|
``` |
|
But if you have a different preferred format that works on one of the models above it will likely still work. |
