File size: 555 Bytes
cf8eac1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
models:
  - model: meta-llama/Meta-Llama-3-8B  # no parameters necessary for base model
  - model: bineric/NorskGPT-Llama3-8b
    parameters:
      density: 0.5  # fraction of weights in differences from the base model to retain
      weight:   # weight gradient
        - filter: mlp
          value: 0.5
        - value: 0
  - model: NousResearch/Hermes-2-Theta-Llama-3-8B
    parameters:
      density: 0.5
      weight: 0.5
merge_method: dare_ties
base_model: meta-llama/Meta-Llama-3-8B
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16