BigQwen2.5-Echo-47B-Instruct / mergekit_config.yml
mlabonne's picture
Add files using upload-large-folder tool
00ee83e verified
raw
history blame
3.88 kB
slices:
# First 8 layers: No replication
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [0, 8]
# Next 8 layers: Replicate 2 layers
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [8, 9]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [8, 9]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [9, 13]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [13, 14]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [13, 14]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [14, 16]
# Next 8 layers: Replicate 4 layers
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [16, 18]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [17, 19]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [18, 20]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [19, 21]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [20, 22]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [21, 23]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [22, 24]
# Next 8 layers: Replicate all 8 layers
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [24, 25]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [24, 26]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [25, 27]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [26, 28]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [27, 29]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [28, 30]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [29, 31]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [30, 32]
# Middle 8 layers: Replicate all 8 layers
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [32, 33]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [32, 34]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [33, 35]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [34, 36]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [35, 37]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [36, 38]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [37, 39]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [38, 40]
# Next 8 layers: Replicate 4 layers
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [40, 42]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [41, 43]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [42, 44]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [43, 45]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [44, 46]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [45, 47]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [46, 48]
# Next 8 layers: Replicate 2 layers
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [48, 49]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [48, 49]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [49, 53]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [53, 54]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [53, 54]
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [54, 56]
# Last 8 layers: No replication
- sources:
- model: Qwen/Qwen2.5-32B-Instruct
layer_range: [56, 64]
merge_method: passthrough
dtype: bfloat16