| dtype: bfloat16 | |
| merge_method: passthrough | |
| slices: | |
| - sources: | |
| - layer_range: [0, 24] | |
| model: princeton-nlp/Llama-3-8B-ProLong-512k-Instruct | |
| - sources: | |
| - layer_range: [8, 24] | |
| model: princeton-nlp/Llama-3-8B-ProLong-512k-Instruct | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 0.0 | |
| - filter: down_proj | |
| value: 0.0 | |
| - value: 1.0 | |
| - sources: | |
| - layer_range: [8, 24] | |
| model: princeton-nlp/Llama-3-8B-ProLong-512k-Instruct | |
| parameters: | |
| scale: | |
| - filter: o_proj | |
| value: 0.0 | |
| - filter: down_proj | |
| value: 0.0 | |
| - value: 1.0 | |
| - sources: | |
| - layer_range: [24, 32] | |
| model: princeton-nlp/Llama-3-8B-ProLong-512k-Instruct | |