Skip to content

Latest commit

 

History

History
38 lines (27 loc) · 1.37 KB

README.md

File metadata and controls

38 lines (27 loc) · 1.37 KB
Raw
license tags license_name license_link pipeline_tag
other
merge
microsoft-research-license
text-generation

OrcaMaid-v3-13b-32k

This is the third version of OrcaMaid, a weighted gradient SLERP merge between Microsoft's Orca-2-13b and NeverSleep's Noromaid-13b-v0.3.

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 32768 via YaRN (original context length was 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