My merges
Collection
A collection of language models I've merged, in chronological order
•
11 items
•
Updated
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}
<s>
</s>
32768
via YaRN (original context length was 4096
)