lejelly/dare-mistral-7b-instrcut-math-code

dare

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

Merge Details

Merge Method

This model was merged using the Linear DARE merge method using mistralai/Mistral-7B-v0.1 as a base.

Models Merged

The following models were included in the merge:

• mistralai/Mistral-7B-Instruct-v0.2
• Nondzu/Mistral-7B-codealpaca-lora
• TIGER-Lab/MAmmoTH2-7B

Configuration

The following YAML configuration was used to produce this model:

# DARE + Average Merging
# random seed: 42
# Each parameter refers to DARE [https://arxiv.org/abs/2311.03099] 
base_model: mistralai/Mistral-7B-v0.1
models:
  - model: mistralai/Mistral-7B-Instruct-v0.2
    parameters:
      density: 0.2
      weight: 1.0
  - model: TIGER-Lab/MAmmoTH2-7B
    parameters:
      density: 0.2
      weight: 1.0
  - model: Nondzu/Mistral-7B-codealpaca-lora
    parameters:
      density: 0.2
      weight: 1.0
merge_method: dare_linear
parameters:
  normalize: true
  lambda: 1.0
  rescale: true
dtype: float16
tokenizer:
  source: union