OrcaMaid-13b

This is a merge of Microsoft's Orca-2-13b and Undi and IkariDev's Noromaid-v0.1.1-13b, with just a touch of Kal'tsit's cat-v1.0 mixed in.

The model recipe was as follows:

  • Linear merge of Orca-2-13b @0.8 and cat-v1.0-13b @0.2 = OrcaCat-13b (no plans to release)
  • Gradient SLERP merge of Noromaid-v0.1.1 @0.5 and OrcaCat-13b @0.5 = OrcaMaid-13b

Both merges were done in FP32 rather than FP16, due to Orca being released as FP32. I didn't want to risk losing any precision.

The overall goal of this merge is to create a model that sounds uniquely human and natural, without sacrificing intelligence. Edit: after some feedback from a few others, ranking on the Ayumi leaderboards, and more of my own testing, I believe I have succeeded as well as I reasonably could have hoped.

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

Thanks

Downloads last month
24
Safetensors
Model size
13B params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for ddh0/OrcaMaid-13b

Quantizations
4 models

Collection including ddh0/OrcaMaid-13b