Llama-2
Collection
3 items
•
Updated
•
1
Restack of the legendary Psyonic Cetacean: jebcarter/psyonic-cetacean-20B
GGUF quants: FaradayDotDev/Space-Whale-Lite-13B-GGUF
This is a merge of pre-trained language models created using mergekit.
This model was merged using the passthrough merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: Orca2-Flat (TeeZee/Orca-2-13b_flat -> float16)
layer_range: [0, 8]
- sources:
- model: KoboldAI/LLaMA2-13B-Psyfighter2
layer_range: [8, 24]
- sources:
- model: Orca2-Flat (TeeZee/Orca-2-13b_flat -> float16)
layer_range: [24, 32]
- sources:
- model: KoboldAI/LLaMA2-13B-Psyfighter2
layer_range: [32, 40]
merge_method: passthrough
dtype: float16