README.md

metadata

base_model:
  - mistralai/Mistral-7B-Instruct-v0.2
  - TIGER-Lab/MAmmoTH2-7B
  - Nondzu/Mistral-7B-codealpaca-lora
  - mistralai/Mistral-7B-v0.1
library_name: transformers
tags:
  - mergekit
  - merge

w1_0_0_w2_0_1_w3_0_3

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
• TIGER-Lab/MAmmoTH2-7B
• Nondzu/Mistral-7B-codealpaca-lora

Configuration

The following YAML configuration was used to produce this model:

# Task Arithmetic - Grid Search
# Weights: 0.0, 0.1, 0.3
base_model: mistralai/Mistral-7B-v0.1
models:
  - model: mistralai/Mistral-7B-Instruct-v0.2
    parameters:
      weight: 0.0
  - model: TIGER-Lab/MAmmoTH2-7B
    parameters:
      weight: 0.1
  - model: Nondzu/Mistral-7B-codealpaca-lora
    parameters:
      weight: 0.3
merge_method: task_arithmetic
parameters:
  normalize: false
  lambda: 1.0
dtype: float16
tokenizer:
  source: union