RichardErkhov/knifeayumu_-_Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP - GGUF

• —Model creator: https://huggingface.co/knifeayumu/
• —Original model: https://huggingface.co/knifeayumu/Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP/

Original model description: --- base_model:

• —TheDrummer/Rocinante-12B-v1
• —crestf411/nemo-sunfall-v0.6.1 library_name: transformers tags:
• —mergekit
• —merge license: apache-2.0 language:
• —en ---

The Drummer x Cute and Funny 12B

This is a merge of pre-trained language models created using mergekit. Did it for fun!

GGUF quants : knifeayumu/Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP-GGUF

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• —TheDrummer/Rocinante-12B-v1
• —crestf411/nemo-sunfall-v0.6.1

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - model: TheDrummer/Rocinante-12B-v1
    layer_range: [0, 40]
  - model: crestf411/nemo-sunfall-v0.6.1
    layer_range: [0, 40]
merge_method: slerp
base_model: TheDrummer/Rocinante-12B-v1
parameters:
  t:
  - filter: self_attn
    value: [0, 0.5, 0.3, 0.7, 1]
  - filter: mlp
    value: [1, 0.5, 0.7, 0.3, 0]
  - value: 0.5
dtype: bfloat16

Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more quants, at much higher speed, than I would otherwise be able to.