wizardllama-7b/README.md

base_model, library_name, tags, license

base_model	library_name	tags	license
codellama/CodeLlama-7b-Python-hf WizardLM/WizardCoder-Python-7B-V1.0	transformers	mergekit merge code	apache-2.0

merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• codellama/CodeLlama-7b-Python-hf
• WizardLM/WizardCoder-Python-7B-V1.0

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: WizardLM/WizardCoder-Python-7B-V1.0
        layer_range: [0, 32]
      - model: codellama/CodeLlama-7b-Python-hf
        layer_range: [0, 32]
merge_method: slerp
base_model: codellama/CodeLlama-7b-Python-hf
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16