| model_name: "post-cursa-o1" | |
| base_model: marcuscedricridia/post-cursa-o1 | |
| 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: marcuscedricridia/pre-cursa-o1-v1.2 | |
| layer_range: [0, 28] | |
| - model: marcuscedricridia/post-cursa-o1 | |
| 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 | |