Qwen1.5B-Instruct-Upscale-3.5B / mergekit_config.yml
Delta-Vector's picture
Upload folder using huggingface_hub
7337097 verified
raw
history blame contribute delete
825 Bytes
slices:
- sources:
- model: Qwen/Qwen2-1.5B-Instruct
layer_range: [0, 24]
- sources: # add middle layers with residuals scaled to zero
- model: Qwen/Qwen2-1.5B-Instruct
layer_range: [8, 24]
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources: # add middle layers with residuals scaled to zero
- model: Qwen/Qwen2-1.5B-Instruct
layer_range: [8, 28]
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- model: Qwen/Qwen2-1.5B-Instruct
layer_range: [24, 28]
merge_method: passthrough
dtype: bfloat16