Views
No views yet

<think> tag. This model's ancestry results in a hybrid thinker that sometimes chooses to think without <think> tags.1models:
2 - model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B
3 parameters:
4 density: 0.8
5 weight: 1.0
6 - model: sophosympatheia/Strawberrylemonade-L3-70B-v1.1
7 parameters:
8 density: 0.5
9 weight: 0.4
10 - model: NeverSleep/Lumimaid-v0.2-70B
11 parameters:
12 density: 0.5
13 weight: 0.4
14merge_method: dare_ties
15base_model: unsloth/Llama-3.3-70B-Instruct
16parameters:
17 normalize: true
18 int8_mask: true
19dtype: bfloat16
20