metadata
base_model:
- NousResearch/Hermes-2-Pro-Mistral-7B
- WizardLM/WizardMath-7B-V1.1
library_name: transformers
tags:
- mergekit
- merge
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: NousResearch/Hermes-2-Pro-Mistral-7B
- model: WizardLM/WizardMath-7B-V1.1
merge_method: slerp
base_model: NousResearch/Hermes-2-Pro-Mistral-7B
dtype: bfloat16
parameters:
t: [0, 0.5, 1, 0.5, 0]
train:
auto_train: true
quantization:
enabled: true
bits: 5
method: "k-means"
subquantizers: 256
output:
format: gguf
filename: entrenado.gguf