Grace0710/kollama3_solarInstruct_merge

new-merged-model

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:

• beomi/Llama-3-Open-Ko-8B
• Upstage/SOLAR-10.7B-Instruct-v1.0

Configuration

The following YAML configuration was used to produce this model:

# slices:
#   - sources:
#       - model: beomi/Llama-3-Open-Ko-8B
#         layer_range: [0, 32]
#       - model: upstage/SOLAR-10.7B-Instruct-v1.0
#         layer_range: [0, 32]
# merge_method: slerp
# base_model: upstage/SOLAR-10.7B-Instruct-v1.0
# 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: float16
# name: upstage-slerp

# models:
#   - model: upstage-slerp
#     parameters:
#       density: [1, 0.7, 0.1] # density gradient
#       weight: 1.0
#   - model: chihoonlee10/T3Q-ko-solar-dpo-v6.0
#     parameters:
#       density: 0.33
#       weight:
#         - filter: mlp
#           value: 0.5
#         - value: 0
# merge_method: ties
# base_model: meta-llama/Meta-Llama-3-8B-Instruct
# parameters:
#   normalize: true
#   int8_mask: true
# dtype: float16
# name: llama3-slerp-ties
slices:
  - sources:
      - model: beomi/Llama-3-Open-Ko-8B
        layer_range: [0, 32]
      - model: Upstage/SOLAR-10.7B-Instruct-v1.0
        layer_range: [0, 32]
merge_method: slerp
base_model: beomi/Llama-3-Open-Ko-8B
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: float16