Configuration Parsing
Warning:
In config.json: "quantization_config.bits" must be an integer
IceAbsintheLoucheV2RP-7b (Ice0.154-15.11-RP)
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:
- icefog72/IceAbsintheRP-7b
- icefog72/IceAbsintheNeatRP-7b
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: G:\FModels\Ice0.150-20.10-RP-ABLv32
layer_range: [0, 32]
- model: H:\FModels\Ice0.150-20.10-RP
layer_range: [0, 32]
merge_method: slerp
base_model: H:\FModels\Ice0.150-20.10-RP
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
- Downloads last month
- 9