Downloads · 30 days
13
14% of all-time downloads
PJMixers-Dev/MN-2407-DSK-V1.0.0-Zeroed-Interleaved-17.7B
MN-2407-DSK-V1.0.0-Zeroed-Interleaved-17.7B is a text generation model from PJMixers-Dev. Use it when you need the model to write or continue text. It is set up for transformers.
1.5x layer count. Needs to be trained. Not useful on it's own, don't bother quantizing this.
Downloads · 30 days
13
14% of all-time downloads
All-time downloads
90
Public
Parameters
17.7B
35.4 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors35.4 GB · 100%
From the Hugging Face model README
1.5x layer count. Needs to be trained. Not useful on it's own, don't bother quantizing this.
merge_method: passthrough
dtype: bfloat16
slices:
# Original first 10 layers (L0-L9)
- sources:
- layer_range: [0, 10]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# "Before Dupe" of L10
- sources:
- layer_range: [10, 11]
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 L10
- sources:
- layer_range: [10, 11]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# "Before Dupe" of L11
- sources:
- layer_range: [11, 12]
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 L11
- sources:
- layer_range: [11, 12]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# "Before Dupe" of L12
- sources:
- layer_range: [12, 13]
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 L12
- sources:
- layer_range: [12, 13]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# "Before Dupe" of L13
- sources:
- layer_range: [13, 14]
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 L13
- sources:
- layer_range: [13, 14]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# "Before Dupe" of L14
- sources:
- layer_range: [14, 15]
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 L14
- sources:
- layer_range: [14, 15]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# "Before Dupe" of L15
- sources:
- layer_range: [15, 16]
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 L15
- sources:
- layer_range: [15, 16]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# "Before Dupe" 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
# "Before Dupe" 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
# "Before Dupe" 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
# "Before Dupe" 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
# Original L20
- sources:
- layer_range: [20, 21]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# "After Dupe" 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 L21
- sources:
- layer_range: [21, 22]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# "After Dupe" 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 L22
- sources:
- layer_range: [22, 23]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# "After Dupe" 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 L23
- sources:
- layer_range: [23, 24]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# "After Dupe" 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 L24
- sources:
- layer_range: [24, 25]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# "After Dupe" of L24
- sources:
- layer_range: [24, 25]
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 L25
- sources:
- layer_range: [25, 26]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# "After Dupe" of L25
- sources:
- layer_range: [25, 26]
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 L26
- sources:
- layer_range: [26, 27]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# "After Dupe" of L26
- sources:
- layer_range: [26, 27]
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 L27
- sources:
- layer_range: [27, 28]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# "After Dupe" of L27
- sources:
- layer_range: [27, 28]
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 L28
- sources:
- layer_range: [28, 29]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# "After Dupe" of L28
- sources:
- layer_range: [28, 29]
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 L29
- sources:
- layer_range: [29, 30]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
# "After Dupe" of L29
- sources:
- layer_range: [29, 30]
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 last 10 layers (L30-L39)
- sources:
- layer_range: [30, 40]
model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b