README.md

metadata

base_model:
  - princeton-nlp/SWE-Llama-7b
  - vibhorag101/llama-2-7b-chat-hf-phr_mental_therapy
  - togethercomputer/LLaMA-2-7B-32K
library_name: transformers
tags:
  - mergekit
  - merge

dave

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

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

• princeton-nlp/SWE-Llama-7b
• vibhorag101/llama-2-7b-chat-hf-phr_mental_therapy
• togethercomputer/LLaMA-2-7B-32K

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: togethercomputer/LLaMA-2-7B-32K
    parameters:
      weight: 1.0
  - model: vibhorag101/llama-2-7b-chat-hf-phr_mental_therapy
    parameters:
      weight: 0.3
  - model: princeton-nlp/SWE-Llama-7b
    parameters:
      weight: 0.5
merge_method: linear
dtype: float16