My merges
Collection
A collection of language models I've merged, in chronological order
•
11 items
•
Updated
This is the fixed version of OrcaMaid-v2-13b, extended to 32768
context length via YaRN. The (now-deleted) v2 model had issues with the merged tokenizer that prevented it from stopping when necessary, and caused it to output broken ChatML tokens like <|im_end
, etc.
This is a gradient SLERP merge of Microsoft's Orca-2-13b and Undi and IkariDev's Noromaid-v0.1.1-13b, biased towards Orca.
Just as with OrcaMaid v1, the overall goal of this merge is to create a model that sounds uniquely human and natural, without sacrificing intelligence.
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
)