Mistral-Nemo-VICIOUS_MESH-12B-2407 / mergekit_config.yml
bamec66557's picture
Upload folder using huggingface_hub
4286500 verified
raw
history blame
4.48 kB
base_model: bamec66557/VICIOUS_MESH-12B-OMEGA
dtype: bfloat16
merge_method: slerp
tokenizer_source: base
# Slices Configuration (Layer-Specific Merging)
slices:
- sources:
- model: bamec66557/VICIOUS_MESH-12B-OMEGA
layer_range: [0, 5]
- model: bamec66557/VICIOUS_MESH-12B-BETA
layer_range: [0, 5]
parameters:
t:
- name: self_attn
value: [0.85, 0.88, 0.91, 0.94, 0.97]
- name: mlp
value: [0.9, 0.92, 0.95, 0.98, 1.0]
- name: layer_norm
value: [0.75, 0.78, 0.81, 0.84, 0.87]
- name: embed_tokens
value: [1.0]
- sources:
- model: bamec66557/VICIOUS_MESH-12B-OMEGA
layer_range: [5, 10]
- model: bamec66557/VICIOUS_MESH-12B-BETA
layer_range: [5, 10]
parameters:
t:
- name: self_attn
value: [0.8, 0.83, 0.86, 0.89, 0.92]
- name: mlp
value: [0.88, 0.91, 0.94, 0.97, 1.0]
- name: layer_norm
value: [0.7, 0.73, 0.76, 0.79, 0.82]
- name: embed_tokens
value: [1.0]
- sources:
- model: bamec66557/VICIOUS_MESH-12B-OMEGA
layer_range: [10, 15]
- model: bamec66557/VICIOUS_MESH-12B-BETA
layer_range: [10, 15]
parameters:
t:
- name: self_attn
value: [0.75, 0.78, 0.81, 0.84, 0.87]
- name: mlp
value: [0.85, 0.88, 0.91, 0.94, 0.97]
- name: layer_norm
value: [0.65, 0.68, 0.71, 0.74, 0.77]
- name: embed_tokens
value: [1.0]
- sources:
- model: bamec66557/VICIOUS_MESH-12B-OMEGA
layer_range: [15, 20]
- model: bamec66557/VICIOUS_MESH-12B-BETA
layer_range: [15, 20]
parameters:
t:
- name: self_attn
value: [0.72, 0.75, 0.78, 0.81, 0.84]
- name: mlp
value: [0.8, 0.83, 0.86, 0.89, 0.92]
- name: layer_norm
value: [0.6, 0.63, 0.66, 0.69, 0.72]
- name: embed_tokens
value: [1.0]
- sources:
- model: bamec66557/VICIOUS_MESH-12B-OMEGA
layer_range: [20, 25]
- model: bamec66557/VICIOUS_MESH-12B-BETA
layer_range: [20, 25]
parameters:
t:
- name: self_attn
value: [0.7, 0.73, 0.76, 0.79, 0.82]
- name: mlp
value: [0.75, 0.78, 0.81, 0.84, 0.87]
- name: layer_norm
value: [0.55, 0.58, 0.61, 0.64, 0.67]
- name: embed_tokens
value: [1.0]
- sources:
- model: bamec66557/VICIOUS_MESH-12B-OMEGA
layer_range: [25, 30]
- model: bamec66557/VICIOUS_MESH-12B-BETA
layer_range: [25, 30]
parameters:
t:
- name: self_attn
value: [0.68, 0.71, 0.74, 0.77, 0.8]
- name: mlp
value: [0.7, 0.73, 0.76, 0.79, 0.82]
- name: layer_norm
value: [0.5, 0.53, 0.56, 0.59, 0.62]
- name: embed_tokens
value: [1.0]
- sources:
- model: bamec66557/VICIOUS_MESH-12B-OMEGA
layer_range: [30, 35]
- model: bamec66557/VICIOUS_MESH-12B-BETA
layer_range: [30, 35]
parameters:
t:
- name: self_attn
value: [0.65, 0.68, 0.71, 0.74, 0.77]
- name: mlp
value: [0.68, 0.71, 0.74, 0.77, 0.8]
- name: layer_norm
value: [0.45, 0.48, 0.51, 0.54, 0.57]
- name: embed_tokens
value: [1.0]
- sources:
- model: bamec66557/VICIOUS_MESH-12B-OMEGA
layer_range: [35, 40]
- model: bamec66557/VICIOUS_MESH-12B-BETA
layer_range: [35, 40]
parameters:
t:
- name: self_attn
value: [0.6, 0.63, 0.66, 0.69, 0.72]
- name: mlp
value: [0.65, 0.68, 0.71, 0.74, 0.77]
- name: layer_norm
value: [0.4, 0.43, 0.46, 0.49, 0.52]
- name: embed_tokens
value: [1.0]
# Regularization
regularization:
- method: weight_clipping
clip_range: [-0.1, 0.1]
- method: random_noise
scale: 0.003
- method: attention_dropout
scale: 0.05
- method: gradient_clipping
clip_norm: 1.0
# Postprocessing
postprocessing:
- operation: non_linear_scaling
parameters:
function: tanh
- operation: sharpening
intensity: 0.4
- operation: gaussian_smoothing
sigma: 1.0
- operation: normalize
- operation: dynamic_scaling
scale_range: [0.85, 1.15]
- operation: smoothing
parameters:
adaptive: true
range: [0.9, 1.1]
kernel_size: 3