Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3.1-minitron-6b-width-base-chatml - GGUF

• Model creator: https://huggingface.co/dumping-grounds/
• Original model: https://huggingface.co/dumping-grounds/llama-3.1-minitron-6b-width-base-chatml/

Original model description:

• IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml

• mergekit
• merge

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:

• IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml
        layer_range: [0, 24]
  - sources: # add middle layers with residuals scaled to zero
      - model: IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml
        layer_range: [8, 24]
        parameters:
          scale:
            - filter: o_proj
              value: 0.0
            - filter: down_proj
              value: 0.0
            - value: 1.0
  - sources:
      - model: IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml
        layer_range: [24, 32]
merge_method: passthrough
dtype: bfloat16