Downloads · 30 days
3
6% of all-time downloads
mergekit-community/mergekit-passthrough-hucyxhl
mergekit-passthrough-hucyxhl is a text generation model from mergekit-community. Use it when you need the model to write or continue text. It is set up for transformers.
This is a merge of pre-trained language models created using mergekit.
Downloads · 30 days
3
6% of all-time downloads
All-time downloads
51
Public
Parameters
14.4B
28.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors28.9 GB · 100%
From the Hugging Face model README
This is a merge of pre-trained language models created using mergekit.
This model was merged using the Passthrough merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
merge_method: passthrough
dtype: bfloat16
slices:
# Original first 16 layers (L0-L15)
- sources:
- layer_range: [0, 16]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# Dupe A of L16
- sources:
- layer_range: [16, 17]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
# Original L16
- sources:
- layer_range: [16, 17]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# Dupe A of L17
- sources:
- layer_range: [17, 18]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
# Original L17
- sources:
- layer_range: [17, 18]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# Dupe A of L18
- sources:
- layer_range: [18, 19]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
# Original L18
- sources:
- layer_range: [18, 19]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# Dupe A of L19
- sources:
- layer_range: [19, 20]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
# Original L19
- sources:
- layer_range: [19, 20]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# Dupe A of L20
- sources:
- layer_range: [20, 21]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
# Original L20
- sources:
- layer_range: [20, 21]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# Dupe A of L21
- sources:
- layer_range: [21, 22]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
# Original L21
- sources:
- layer_range: [21, 22]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# Dupe A of L22
- sources:
- layer_range: [22, 23]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
# Original L22
- sources:
- layer_range: [22, 23]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# Dupe A of L23
- sources:
- layer_range: [23, 24]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
# Original L23
- sources:
- layer_range: [23, 24]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# Original last 16 layers (L24-L39)
- sources:
- layer_range: [24, 40]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b