| base_model: kawagoshi-llm-team/llma3_manydata_our_data_rope | |
| dtype: float16 | |
| merge_method: dare_ties | |
| parameters: | |
| int8_mask: 1.0 | |
| normalize: 1.0 | |
| slices: | |
| - sources: | |
| - layer_range: [0, 8] | |
| model: kawagoshi-llm-team/llma3_manydata_our_data_rope | |
| parameters: | |
| density: 0.7653375506603464 | |
| weight: 0.13767610478325062 | |
| - layer_range: [0, 8] | |
| model: kawagoshi-llm-team/llma3_manydata_not_our_data_rope | |
| parameters: | |
| density: 0.7336602489449524 | |
| weight: 0.3666639544856324 | |
| - layer_range: [0, 8] | |
| model: kawagoshi-llm-team/llama3_sft_many_chat | |
| parameters: | |
| density: 1.0 | |
| weight: 0.3030835610677404 | |
| - sources: | |
| - layer_range: [8, 16] | |
| model: kawagoshi-llm-team/llma3_manydata_our_data_rope | |
| parameters: | |
| density: 0.9861387586510485 | |
| weight: 0.3948174181228292 | |
| - layer_range: [8, 16] | |
| model: kawagoshi-llm-team/llma3_manydata_not_our_data_rope | |
| parameters: | |
| density: 0.8413699662162298 | |
| weight: 0.45739982954282526 | |
| - layer_range: [8, 16] | |
| model: kawagoshi-llm-team/llama3_sft_many_chat | |
| parameters: | |
| density: 1.0 | |
| weight: 0.30274586211044396 | |
| - sources: | |
| - layer_range: [16, 24] | |
| model: kawagoshi-llm-team/llma3_manydata_our_data_rope | |
| parameters: | |
| density: 0.9503146891835705 | |
| weight: 0.2849061463174477 | |
| - layer_range: [16, 24] | |
| model: kawagoshi-llm-team/llma3_manydata_not_our_data_rope | |
| parameters: | |
| density: 0.832031377573231 | |
| weight: 0.6047693096979141 | |
| - layer_range: [16, 24] | |
| model: kawagoshi-llm-team/llama3_sft_many_chat | |
| parameters: | |
| density: 0.9442991059236329 | |
| weight: 0.4002445342115458 | |
| - sources: | |
| - layer_range: [24, 32] | |
| model: kawagoshi-llm-team/llma3_manydata_our_data_rope | |
| parameters: | |
| density: 0.8517897851608993 | |
| weight: 0.3362716927810899 | |
| - layer_range: [24, 32] | |
| model: kawagoshi-llm-team/llma3_manydata_not_our_data_rope | |
| parameters: | |
| density: 1.0 | |
| weight: 0.2909336827183003 | |
| - layer_range: [24, 32] | |
| model: kawagoshi-llm-team/llama3_sft_many_chat | |
| parameters: | |
| density: 1.0 | |
| weight: 0.3474712168573882 | |
| - sources: | |
| - layer_range: [32, 40] | |
| model: kawagoshi-llm-team/llma3_manydata_our_data_rope | |
| parameters: | |
| density: 1.0 | |
| weight: 0.27727322046805786 | |
| - layer_range: [32, 40] | |
| model: kawagoshi-llm-team/llma3_manydata_not_our_data_rope | |
| parameters: | |
| density: 0.8394275769864135 | |
| weight: 0.4724670213437233 | |
| - layer_range: [32, 40] | |
| model: kawagoshi-llm-team/llama3_sft_many_chat | |
| parameters: | |
| density: 1.0 | |
| weight: 0.31333702280148296 | |
| tokenizer_source: base | |