My merges
Collection
A collection of language models I've merged, in chronological order
•
11 items
•
Updated
This is Jeb Carter's Psyonic-Cetacean-20B, merged with Undi's no_robots-alpaca LoRA and extended to 10240
context length via YaRN.
The overall goal of this merge was to create a model with the unique brain of Psyonic-Cetacean and the human voice of the no_robots dataset, that would remain capable at long contexts.
The prompt format is Alpaca. You can use the standard format as shown, but for best results, I strongly recommend customizing 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>
10240
via YaRN (original context length was 4096
)