Exllama 2 version of model created by the work of Undi95

Original Card https://huggingface.co/Undi95/U-Amethyst-20B

Requires ExllamaV2, which is being developed by turboderp https://github.com/turboderp/exllamav2 under an MIT license.

Main branch is 5bpw 6h


image/png

Attempt to recreate Amethyst-13B but in 20B. The two model was glued together with a sparkle of Unholy.

In addition, LimaRP v3 was used, is it recommanded to read the documentation.

Description

This repo contains fp16 files of Amethyst-20B.

Models and loras used

  • Xwin-LM/Xwin-LM-13B-V0.1
  • The-Face-Of-Goonery/Huginn-13b-FP16
  • zattio770/120-Days-of-LORA-v2-13B
  • lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT
  • Undi95/Unholy-v1-12L-13B

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

LimaRP v3 usage and suggested settings

image/png

You can follow these instruction format settings in SillyTavern. Replace tiny with your desired response length:

image/png

Special thanks to Sushi.

If you want to support me, you can here.

Downloads last month
7
Inference Providers NEW
Inference Providers available for this model are disabled. Settings