metadata
base_model:
- HPAI-BSC/Llama3.1-Aloe-Beta-70B
- Writer/Palmyra-Med-70B-32K
- sam-paech/Llama-3.3-70B-Instruct-ftpo_1k
- schonsense/IPOplectic
library_name: transformers
tags:
- mergekit
- merge
sce_med
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SCE merge method using sam-paech/Llama-3.3-70B-Instruct-ftpo_1k as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
merge_method: sce
select_topk: 0.25
models:
- model: sam-paech/Llama-3.3-70B-Instruct-ftpo_1k
- model: HPAI-BSC/Llama3.1-Aloe-Beta-70B
- model: Writer/Palmyra-Med-70B-32K
- model: schonsense/IPOplectic
base_model: sam-paech/Llama-3.3-70B-Instruct-ftpo_1k
parameters:
normalize: false
int8_mask: true
dtype: float32
out_dtype: bfloat16
tokenizer:
source: base
pad_to_multiple_of: 8