Views
No views yet
1base_model: /root/finetuneqwen/distillgpt7SJvM
2dtype: bfloat16
3merge_method: dare_ties
4modules:
5 default:
6 slices:
7 - sources:
8 - layer_range: [0, 64]
9 model: /root/finetuneqwen/prexpertMJDD
10 parameters:
11 weight: 0.5
12 - layer_range: [0, 64]
13 model: /root/finetuneqwen/distillgpt7SJvM
14 parameters:
15 weight: 0.5
16parameters:
17 density: 0.8
18 int8_mask: 0.0
19 normalize: 1.0
20tokenizer_source: base