Alpacazord-Viking-7B-exl2-4bpw

This is an ExLlamaV2 quantized model in 4bpw of mpasila/Alpacazord-Viking-7B using the default calibration dataset.

Original Model card:

Model Card for Alpacazord-Viking-7B

This is a merge of mpasila/Alpacazord-Viking-LoRA-7B.

LoRA trained with text-generation-webui in 4-bit using LumiOpen/Viking-7B as the base model for 1 epoch. Dataset used with the LoRA is mpasila/Alpacazord-V1.

It uses Alpaca format like so:

{
    "instruction,output": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n%instruction%\n\n### Response:\n%output%",
    "instruction,input,output": "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\n%instruction%\n\n### Input:\n%input%\n\n### Response:\n%output%"
}

Merged using this Colab notebook. It might not be the best way to merge a quantized LoRA on to a float16 model but I just wanted to quickly do something. You can try merging it better if you want.

Evaluation

Source

FIN-bench scores:

Will add later. And possibly other evals?????

Framework versions

• PEFT 0.8.2