README.md

metadata

base_model:
  - LeroyDyer/Mixtral_AI_MediTron
  - LeroyDyer/Mixtral_AI_CyberTron
library_name: transformers
tags:
  - mergekit
  - merge
  - code
  - biology
  - chemistry
  - medical
  - not-for-all-audiences
  - text-generation-inference
  - legal
  - finance
datasets:
  - medalpaca/medical_meadow_pubmed_causal
  - ruslanmv/ai-medical-chatbot
  - medalpaca/medical_meadow_mediqa

not the highest of the collection but (secretly the leader as all loras will be pplied to this model; etc as i work its this model will be improved towards growing the other mdoels of which may skew!)

merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• LeroyDyer/Mixtral_AI_MediTron
• LeroyDyer/Mixtral_AI_CyberTron

Configuration

The following YAML configuration was used to produce this model:

  slices:
    - sources:
        - model: LeroyDyer/Mixtral_AI_MediTron
          layer_range: [0, 32]
        - model: LeroyDyer/Mixtral_AI_CyberTron
          layer_range: [0, 32]
  merge_method: slerp
  base_model: LeroyDyer/Mixtral_AI_CyberTron
  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