Initial release
This commit is contained in:
30
mergekit_config.yml
Normal file
30
mergekit_config.yml
Normal file
@@ -0,0 +1,30 @@
|
||||
slices:
|
||||
- sources:
|
||||
- model: princeton-nlp/Llama-3-Instruct-8B-SimPO
|
||||
layer_range:
|
||||
- 0
|
||||
- 32
|
||||
- model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3
|
||||
layer_range:
|
||||
- 0
|
||||
- 32
|
||||
merge_method: slerp
|
||||
base_model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3
|
||||
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
|
||||
Reference in New Issue
Block a user