This merge was done for and with the idea of IkariDev.

This is a variant of ReMM v2 with more SpicyBoros weight as a base.

Explaination :

ReMM-variant-part1: (Chronos-Beluga v2/Hermes)
=> Keeping The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16
=> Keeping NousResearch/Nous-Hermes-Llama2-13b

ReMM-variant-part2: (Huginn/Spicyboros)
=> Keeping jondurbin/spicyboros-13b-2.2 (More weight)
=> Keeping The-Face-Of-Goonery/Huginn-13b-v1.2

With that :
ReMM-v2-variant: (ReML-part1/ReML-part2)
=> Will result in : Chronos-Beluga-v2-13bfp16 / Nous-Hermes-Llama2-13b / spicyboros-13b-2.2 (More weight/Base) / Huginn-13b-v1.2

Description

This repo contains quantized files of ReMM v2 VARIANT, a variant for ReMM v2.

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

Prompt template: Alpaca

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

### Instruction:
{prompt}

### Response:
Downloads last month
5
GGUF
Model size
13B params
Architecture
llama

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .