PCB-NRSheared-1

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the DELLA merge method using huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated as a base.

Models Merged

The following models were included in the merge:

• AlSamCur123/Mistral-Small3-24B-InstructContinuedFine
• trashpanda-org/MS-24B-Instruct-Mullein-v0

Configuration

The following YAML configuration was used to produce this model:

# 文件名: pcb_della_merge.yaml
merge_method: della  # 基于DELLA的自适应剪裁
base_model: huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
models:
  - model: trashpanda-org/MS-24B-Instruct-Mullein-v0
    parameters:
      weight: 1.0  # 添加默认权重
      # PCB策略：限制层影响范围 + 动态竞争平衡
      layers:
        - layers: "8-16"
          parameter_name: density
          value: 0.4
        - layers: "8-16"
          parameter_name: epsilon
          value: 0.15
        - layers: "8-16"
          parameter_name: lambda
          value: 1.5
        - layers: "17-24"
          parameter_name: density
          value: 0.2
      variance_threshold: 0.3

  - model: AlSamCur123/Mistral-Small3-24B-InstructContinuedFine
    parameters:
      weight: 1.0  # 添加默认权重
      # 强化指令理解层
      layers:
        - layers: "0-12"
          parameter_name: density
          value: 0.7
        - layers: "0-12"
          parameter_name: epsilon
          value: 0.05
        - layers: "0-12"
          parameter_name: lambda
          value: 2.0
      variance_threshold: 0.25

  - model: huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
    parameters:
      weight: 1.0  # 添加默认权重
      # 基模型参数保护策略
      density: 0.9          # 全局密度 (可能需要单独处理)
      layers:
        - layers: "12-24"
          parameter_name: density
          value: 1.0

parameters:
  global_density: 0.55      # 全局剪裁密度（PCB平衡点）
  intra_balance: true
  variance_threshold: 0.2
  epsilon_range: [0.1, 0.2]

tokenizer:
  source: base

# 参数压缩设置（实现12-13B目标）
architecture:
  hidden_size: 4096
  intermediate_size: 11008
  num_attention_heads: 32
  num_hidden_layers: 30