Llama-3.1-8B-Instruct-abliterated_via_adapter/mergekit_config.yml at main - Llama-3.1-8B-Instruct-abliterated_via_adapter - Gitea: Git with a cup of tea

jinmrong/Llama-3.1-8B-Instruct-abliterated_via_adapter

Files

ModelHub XC a402424c8a 初始化项目，由ModelHub XC社区提供模型

Model: jinmrong/Llama-3.1-8B-Instruct-abliterated_via_adapter
Source: Original Platform

2026-05-01 11:36:08 +08:00

12 lines

346 B

YAML

Raw Permalink Blame History

 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
 dtype: bfloat16
 merge_method: task_arithmetic
 parameters:
   normalize: false
 slices:
 - sources:
   - layer_range: [0, 32]
     model: meta-llama/Meta-Llama-3.1-8B-Instruct+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
     parameters:
       weight: 1.0