model_name: "olmner-o1-7b" | |
base_model: Xiaojian9992024/Qwen2.5-THREADRIPPER-Small | |
merge_method: slerp | |
dtype: bfloat16 | |
tokenizer_source: "union" # or "base" or a model path | |
chat_template: "auto" # or a template name or Jinja2 template | |
slices: | |
- sources: | |
- model: Xiaojian9992024/Qwen2.5-THREADRIPPER-Small | |
layer_range: [0, 28] | |
- model: marcuscedricridia/olmner-della-7b | |
layer_range: [0, 28] | |
parameters: | |
t: | |
- filter: self_attn | |
value: [0.0, 0.3, 0.5, 0.7, 1.0] | |
- filter: mlp | |
value: [1.0, 0.7, 0.5, 0.3, 0.0] | |
- filter: input_layernorm|post_attention_layernorm | |
value: 0.5 | |
- value: 0.5 | |