|
merge_method: passthrough |
|
slices: |
|
- sources: |
|
- layer_range: [0, 19] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [19, 20] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [19, 20] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [19, 20] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [20, 21] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [20, 21] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [20, 21] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [21, 22] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [21, 22] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [21, 22] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [22, 23] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [22, 23] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [22, 23] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [23, 24] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [23, 24] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [23, 24] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [24, 25] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [24, 25] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [24, 25] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [25, 26] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [25, 26] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [25, 26] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [26, 27] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [26, 27] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [26, 27] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [27, 28] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [27, 28] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [27, 28] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [28, 29] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [28, 29] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [28, 29] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [29, 30] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [29, 30] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [29, 30] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [30, 31] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [30, 31] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [30, 31] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [31, 32] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [31, 32] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [31, 32] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [32, 33] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [32, 33] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [32, 33] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [33, 34] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [33, 34] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [33, 34] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [34, 35] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [34, 35] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [34, 35] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [35, 36] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [35, 36] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [35, 36] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [36, 37] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [36, 37] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [36, 37] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [37, 38] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [37, 38] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [37, 38] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [38, 39] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [38, 39] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [38, 39] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [39, 40] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [39, 40] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [39, 40] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [40, 41] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
|
|
- sources: |
|
- layer_range: [40, 41] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [40, 41] |
|
model: unsloth/Mistral-Small-Instruct-2409 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
|
|
- sources: |
|
- layer_range: [41, 55] |
|
model: unsloth/Mistral-Small-Instruct-2409 |