Views
No views yet
1models:
2 - model: unsloth/Mistral-Small-24B-Base-2501
3 - model: unsloth/Mistral-Small-24B-Instruct-2501+ToastyPigeon/new-ms-rp-test-ws
4 parameters:
5 select_topk:
6 - value: [0.05, 0.03, 0.02, 0.02, 0.01]
7 - model: unsloth/Mistral-Small-24B-Instruct-2501+estrogen/MS2501-24b-Ink-ep2-adpt
8 parameters:
9 select_topk: 0.1
10 - model: trashpanda-org/MS-24B-Instruct-Mullein-v0
11 parameters:
12 select_topk: 0.4
13base_model: unsloth/Mistral-Small-24B-Base-2501
14merge_method: sce
15parameters:
16 int8_mask: true
17 rescale: true
18 normalize: true
19dtype: bfloat16
20tokenizer_source: base1dtype: bfloat16
2tokenizer_source: base
3merge_method: della_linear
4parameters:
5 density: 0.55
6base_model: Step1
7models:
8 - model: unsloth/Mistral-Small-24B-Instruct-2501
9 parameters:
10 weight:
11 - filter: v_proj
12 value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
13 - filter: o_proj
14 value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
15 - filter: up_proj
16 value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
17 - filter: gate_proj
18 value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
19 - filter: down_proj
20 value: [1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
21 - value: 0
22 - model: Step1
23 parameters:
24 weight:
25 - filter: v_proj
26 value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
27 - filter: o_proj
28 value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
29 - filter: up_proj
30 value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
31 - filter: gate_proj
32 value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
33 - filter: down_proj
34 value: [0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1]
35 - value: 1