TunyTrinh/ghost_neural3_1_1_08_07_00

Test_model2

Test_model2 is a merge of the following models using mergekit:

• ghost-x/ghost-7b-v0.9.1
• Intel/neural-chat-7b-v3-3

🧩 Configuration

slices:
  - sources:
      - model: ghost-x/ghost-7b-v0.9.1
        layer_range: [0, 32]
      - model: Intel/neural-chat-7b-v3-3
        layer_range: [0, 32]
merge_method: slerp
base_model: ghost-x/ghost-7b-v0.9.1
parameters:
  t:
    - filter: self_attn
      value: [1.0, 1.0, 0.8, 0.7, 0.0]
    - filter: mlp
      value: [0.0, 0.0, 0.2, 0.3, 1.0]
    - value: 0.5
  embed_slerp: true
dtype: bfloat16