EstherXC/llama_tie

llama_pro_base_dare_tie

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

Merge Details

Merge Method

This model was merged using the TIES merge method using NousResearch/Llama-2-7b-hf as a base.

Models Merged

The following models were included in the merge:

• dnagpt/llama-dna
• GreatCaptainNemo/ProLLaMA

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: NousResearch/Llama-2-7b-hf
  - model: GreatCaptainNemo/ProLLaMA #wanglab/mixtral_7b_dna_pretrain
    parameters:
      density: 0.5
      weight: 0.2
  - model: dnagpt/llama-dna #EstherXC/mixtral_7b_protein_pretrain
    parameters:
      density: 0.5
      weight: 0.2
merge_method: ties
base_model: NousResearch/Llama-2-7b-hf #wanglab/mixtral_7b_dna_pretrain
parameters:
  normalize: true
dtype: float16