metadata
base_model:
- codellama/CodeLlama-34b-Instruct-hf
- Phind/Phind-CodeLlama-34B-v2
library_name: transformers
tags:
- mergekit
- merge
merge-legacy
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 codellama/CodeLlama-34b-Instruct-hf as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: codellama/CodeLlama-34b-Instruct-hf
parameters:
density: [1, 0.7, 0.1] # density gradient
weight: 1.0
- model: Phind/Phind-CodeLlama-34B-v2
parameters:
density: 0.5
weight: [0, 0.3, 0.7, 1] # weight gradient
merge_method: dare_ties
base_model: codellama/CodeLlama-34b-Instruct-hf
parameters:
normalize: true
int8_mask: true
dtype: float16