Hjgugugjhuhjggg/mergekit-linear-hdsgwby

merge

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

Merge Details

Merge Method

This model was merged using the linear merge method using huihui-ai/Llama-3.2-1B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

• huihui-ai/MicroThinker-1B-Preview
• Hjgugugjhuhjggg/llama-3.2-1B-spinquant-hf

Configuration

The following YAML configuration was used to produce this model:

models:
  - layer_range: [0, 1]
    model: huihui-ai/Llama-3.2-1B-Instruct-abliterated
    parameters:
      weight: 1
      density: 0.9
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100

  - layer_range: [0, 1]
    model: huihui-ai/MicroThinker-1B-Preview
    parameters:
      weight: 1
      density: 0.9
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100

  - layer_range: [0, 1]
    model: Hjgugugjhuhjggg/llama-3.2-1B-spinquant-hf
    parameters:
      weight: 1
      density: 0.9
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        - method: int8
          value: 100
        - method: int4
          value: 100

merge_method: linear
base_model: huihui-ai/Llama-3.2-1B-Instruct-abliterated
weight: 1
density: 0.9
gamma: 0.01
normalize: true
int8_mask: true
random_seed: 0
temperature: 0.5
top_p: 0.65
inference: true
max_tokens: 999999999
stream: true
quantization:
- method: int8
  value: 100
- method: int4
  value: 100
parameters:
  weight: 1
  density: 0.9
  gamma: 0.01
  normalize: true
  int8_mask: true
  random_seed: 0
  temperature: 0.5
  top_p: 0.65
  inference: true
  max_tokens: 999999999
  stream: true
  quantization:
    - method: int8
      value: 100
    - method: int4
      value: 100
dtype: float16