Qwen2.5-7B-M-v1 / mergekit_config.yml
mssongit's picture
Upload merged Qwen2.5-7B CPT Train(BF16)
1598a53 verified
raw
history blame
491 Bytes
base_model: KoFinanceLLM/Qwen2.5-7B-CPT-Merge
dtype: bfloat16
merge_method: ties
parameters:
density: 1.0
int8_mask: 1.0
normalize: 1.0
weight: 1.0
slices:
- sources:
- layer_range: [0, 28]
model: KoFinanceLLM/KRX-Qwen2.5-7B-SFT-MultiHiertt
parameters:
density: 1.0
weight: 1.0
- layer_range: [0, 28]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
density: 1.0
weight: 1.0
- layer_range: [0, 28]
model: KoFinanceLLM/Qwen2.5-7B-CPT-Merge