Lunzima/MilkyLoong-Qwen2.5-1.5B-base1

merge

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 huihui-ai/Qwen2.5-1.5B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

• bond005/meno-tiny-0.1
• Youlln/ECE-PRYMMAL-YL-1B-SLERP-V2
• goulue5/merging_LLM
• godlikehhd/alpaca_data_ifd_min_2600
• godlikehhd/alpaca_data_score_max_2500
• Youlln/ECE-PRYMMAL-YL-1B-SLERP-V1
• Sakalti/Saba1.5-1.5B
• fblgit/miniclaus-qw1.5B-UNAMGS-GRPO

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: bond005/meno-tiny-0.1
  - model: fblgit/miniclaus-qw1.5B-UNAMGS-GRPO
  - model: Sakalti/Saba1.5-1.5B
  - model: goulue5/merging_LLM
  - model: Youlln/ECE-PRYMMAL-YL-1B-SLERP-V1
  - model: Youlln/ECE-PRYMMAL-YL-1B-SLERP-V2
  - model: godlikehhd/alpaca_data_ifd_min_2600
  - model: godlikehhd/alpaca_data_score_max_2500
  - model: huihui-ai/Qwen2.5-1.5B-Instruct-abliterated
merge_method: sce
base_model: huihui-ai/Qwen2.5-1.5B-Instruct-abliterated
dtype: bfloat16
parameters:
  int8_mask: true