Sarvam_updated
Sarvam_updated is a merge of the following models using mergekit:
🧩 Configuration
slices:
- sources:
- model: sarvamai/shuka_v1
layer_range: [0, 32]
- model: sarvamai/sarvam-1
layer_range: [0, 32]
merge_method: slerp
base_model: sarvamai/sarvam-1
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