lejelly/task-wise-llm-adamerge-crossentropy-mistral-7b-instrcut-math-code

task-wise-crossentropy

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

Merge Details

Merge Method

This model was merged using the Task Arithmetic 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:

# task-wise LLM-AdaMerge with cross-entropy loss
base_model: mistralai/Mistral-7B-v0.1
models:
  - model: mistralai/Mistral-7B-Instruct-v0.2
    parameters:
      weight: 0.10558585822582245
  - model: TIGER-Lab/MAmmoTH2-7B
    parameters:
      weight: 0.45740658044815063
  - model: Nondzu/Mistral-7B-codealpaca-lora
    parameters:
      weight: 0.5316656231880188
merge_method: task_arithmetic
parameters:
  normalize: false
  lambda: 1.0
dtype: float16
tokenizer:
  source: union