FuseChat: Knowledge Fusion of Chat Models
Paper
•
2408.07990
•
Published
•
14
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SCE merge method using D:\mergekit\yamls\IPOplectic as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
merge_method: sce
select_topk: 0.25
models:
- model: "D:\\mergekit\\yamls\\IPOplectic"
- model: NousResearch/Hermes-4-70B
- model: "D:\\mergekit\\yamls\\flu"
- model: "D:\\mergekit\\yamls\\smrt"
- model: schonsense/Bragi_v2_70B
base_model: "D:\\mergekit\\yamls\\IPOplectic"
parameters:
normalize: false
int8_mask: true
dtype: float32
out_dtype: bfloat16
tokenizer:
source: union
pad_to_multiple_of: 8