metadata
base_model:
- Saxo/Linkbricks-Horizon-AI-Japanese-Pro-V5-70B
- tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3
library_name: transformers
tags:
- mergekit
- merge
Linkbricks-Horizon-AI-Japanese-Pro-V7-70B
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:
base_model: Saxo/Linkbricks-Horizon-AI-Japanese-Pro-V5-70B
dtype: bfloat16
merge_method: slerp
parameters:
t:
- filter: self_attn
value: [0.0, 0.5, 0.3, 0.7, 1.0]
- filter: mlp
value: [1.0, 0.5, 0.7, 0.3, 0.0]
- value: 0.8
slices:
- sources:
- layer_range: [0, 80]
model: tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3
- layer_range: [0, 80]
model: Saxo/Linkbricks-Horizon-AI-Japanese-Pro-V5-70B
tokenizer_source: union