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 Qwen/Qwen2.5-7B-Instruct-1M as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
merge_method: sce
models:
- model: marcuscedricridia/Hush-Qwen2.5-7B-RP-v1.3
base_model: Qwen/Qwen2.5-7B-Instruct-1M
parameters:
select_topk: 1
dtype: bfloat16
tokenizer_source: base
normalize: true
int8_mask: true
name: Hush-Qwen2.5-7B-RP-v1.3-1M