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

Update 2023-12-19

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:

1. 1.mistralai/Mistral-7B-Instruct-v0.2
2. 2.ehartford/dolphin-2.2.1-mistral-7b
3. 3.SciPhi/SciPhi-Mistral-7B-32k
4. 4.ehartford/samantha-1.2-mistral-7b
5. 5.Arc53/docsgpt-7b-mistral
6. 6.berkeley-nest/Starling-LM-7B-alpha
7. 7.Q-bert/MetaMath-Cybertron-Starling
8. 8.Open-Orca/Mistral-7B-OpenOrca
9. 9.v1olet/v1olet_marcoroni-go-bruins-merge-7B
10. 10.beowolx/MistralHermes-CodePro-7B-v1
11. 11.TIGER-Lab/MAmmoTH-7B-Mistral
12. 12.teknium/OpenHermes-2.5-Mistral-7B
13. 13.Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
14. 14.mlabonne/NeuralHermes-2.5-Mistral-7B

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

The yaml config file for this model is here:

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