chihoonlee10/T3Q-Merge-SOLAR12

T3Q-Merge-SOLAR12

T3Q-Merge-SOLAR12 is a merge of the following models using mergekit:

• davidkim205/komt-solar-10.7b-sft-v5
• LDCC/LDCC-SOLAR-10.7B

Model Developers Chihoon Lee(chlee10), T3Q

  
  slices:
      - sources:
        - model: davidkim205/komt-solar-10.7b-sft-v5
          layer_range: [0, 48]
        - model: LDCC/LDCC-SOLAR-10.7B
          layer_range: [0, 48]
  
  merge_method: slerp
  base_model: davidkim205/komt-solar-10.7b-sft-v5
  
  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 # fallback for rest of tensors
      
  dtype: bfloat16