metadata
library_name: transformers
tags:
- mergekit
- merge
- llama-cpp
- gguf-my-repo
- solar
- llama
- not-for-all-audiences
base_model: v000000/SyntheticMoist-11B
RP Model, Experimental Solar merge. Alpaca/Vicuna format.
v000000/SyntheticMoist-11B-Q6_K-GGUF
This model was converted to GGUF format from v000000/SyntheticMoist-11B using llama.cpp via the ggml.ai's GGUF-my-repo space.
Refer to the original model card for more details on the model.
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the DARE TIES merge method using upstage/SOLAR-10.7B-v1.0 as a base.
Models Merged
The following models were included in the merge:
- Himitsui/Kaiju-11B
- TheDrummer/Moistral-11B-v3
- Himitsui/MedMitsu-Instruct-11B
- migtissera/Synthia-v3.0-11B
Configuration
The following YAML configuration was used to produce this model:
models:
- model: Himitsui/MedMitsu-Instruct-11B
parameters:
weight: 0.16
density: 0.42
- model: Himitsui/Kaiju-11B
parameters:
weight: 0.22
density: 0.54
- model: migtissera/Synthia-v3.0-11B
parameters:
weight: 0.28
density: 0.66
- model: TheDrummer/Moistral-11B-v3
parameters:
weight: 0.34
density: 0.78
merge_method: dare_ties
base_model: upstage/SOLAR-10.7B-v1.0
parameters:
int8_mask: true
dtype: bfloat16