In light of dataset contamination issue among the merged models raised by the community in recent days, in particular berkeley-nest/Starling-LM-7B-alpha, Q-bert/MetaMath-Cybertron-Starling, and janai-hq/trinity-v1, we decided to remake another model without the models mentioned. Additionally, their CC-by-NC-4.0 license is restrictive and thus are not suitable for an open model.

Model Description

This is an experiment to test merging 14 models using DARE TIES 🦙

The merged model is then merged again with janai-hq/trinity-v1 using Gradient SLERP. The result is a base model that performs quite well but requires some further instruction fine-tuning.

The 14 models are as follows:

base model: mistralai/Mistral-7B-v0.1

The yaml config file for this model is here:

yaml

slices:
  - sources:
      - model: EmbeddedLLM/Mistral-7B-Merge-14-v0
        layer_range: [0, 32]
      - model: janai-hq/trinity-v1
        layer_range: [0, 32]
merge_method: slerp
base_model: EmbeddedLLM/Mistral-7B-Merge-14-v0
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

EmbeddedLLM/Mistral-7B-Merge-14-v0.1

Update 2023-12-19

Model Description

EmbeddedLLM/
Mistral-7B-Merge-14-v0.1