EstopianOrcaMaid-13b

EstopianOrcaMaid-13b

This is a merge of pre-trained language models created using mergekit.

The goal of this merge is to create an unusually intelligent and human-like model especially for RP.

The prompt format is Alpaca. You can use the standard format as shown, but for best results, you should customize the system prompt to your specific needs.

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

### Instruction:
{YOUR MESSAGE HERE}

### Response:
{BOT MESSAGE HERE}

Misc. information

• BOS token is <s>
• EOS token is </s>
• Native context length is 4096
• Base model is Llama 2
• Due to the inclusion of Orca-2-13b, the model is subject to the terms of the Microsoft Research License

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

• KatyTheCutie/EstopianMaid-13B
• microsoft/Orca-2-13b

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /Volumes/Sabrent/LLMs/EstopianMaid-13B
    parameters:
      weight: 0.8
  - model: "/Volumes/SanDisk/LLM Archive/Orca-2-13b"
    parameters:
      weight: 0.2
merge_method: linear
dtype: float16

Thanks

• Thanks to Katy Vetteriano for EstopianMaid-13B