metadata
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- bigcode/starcoder2-7b
- NousResearch/Llama-2-7b-chat-hf
starllama
starllama is a merge of the following models using mergekit:
🧩 Configuration
slices:
- sources:
- model: bigcode/starcoder2-7b
layer_range: [0, 32]
- model: NousResearch/Llama-2-7b-chat-hf
layer_range: [0, 32]
merge_method: slerp
base_model: NousResearch/Llama-2-7b-hf
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