Hjgugugjhuhjggg/mergekit-passthrough-trdtyuc

merge

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

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

• meta-llama/Llama-3.2-1B-Instruct

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - layer_range: [0, 10]
        model: meta-llama/Llama-3.2-1B-Instruct
        parameters:
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
        normalize: true
        int8_mask: true
        density: 0.5
        weight: 0.1
        random_seed: 0
        temperature: 0.5
        top_p: 0.65
        inference: true
        max_tokens: 999999999
        stream: true

  - sources:
      - layer_range: [0, 10]
        model: meta-llama/Llama-3.2-1B-Instruct
        parameters:
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
        normalize: true
        int8_mask: true
        density: 0.5
        weight: 0.1
        random_seed: 0
        temperature: 0.5
        top_p: 0.65
        inference: true
        max_tokens: 999999999
        stream: true

  - sources:
      - layer_range: [0, 10]
        model: meta-llama/Llama-3.2-1B-Instruct
        parameters:
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
        normalize: true
        int8_mask: true
        density: 0.5
        weight: 0.1
        random_seed: 0
        temperature: 0.5
        top_p: 0.65
        inference: true
        max_tokens: 999999999
        stream: true

  - sources:
      - layer_range: [0, 10]
        model: meta-llama/Llama-3.2-1B-Instruct
        parameters:
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
        normalize: true
        int8_mask: true
        density: 0.5
        weight: 0.1
        random_seed: 0
        temperature: 0.5
        top_p: 0.65
        inference: true
        max_tokens: 999999999
        stream: true

  - sources:
      - layer_range: [0, 10]
        model: meta-llama/Llama-3.2-1B-Instruct
        parameters:
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
        normalize: true
        int8_mask: true
        density: 0.5
        weight: 0.1
        random_seed: 0
        temperature: 0.5
        top_p: 0.65
        inference: true
        max_tokens: 999999999
        stream: true

  - sources:
      - layer_range: [0, 10]
        model: meta-llama/Llama-3.2-1B-Instruct
        parameters:
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
        normalize: true
        int8_mask: true
        density: 0.5
        weight: 0.1
        random_seed: 0
        temperature: 0.5
        top_p: 0.65
        inference: true
        max_tokens: 999999999
        stream: true

parameters: 
  normalize: true
  int8_mask: true
  density: 0.5
  weight: 0.1
  random_seed: 0
  temperature: 0.5
  top_p: 0.65
  inference: true
  max_tokens: 999999999
  stream: true
normalize: true
int8_mask: true
density: 0.5
weight: 0.1
random_seed: 0
temperature: 0.5
top_p: 0.65
inference: true
max_tokens: 999999999
stream: true
merge_method: passthrough
dtype: bfloat16