--- models: - model: part3 - model: part1 - model: part2 merge_method: model_stock base_model: part3 parameters: normalize: true int8_mask: true dtype: float16 license: llama3 --- This is a merge stock of 3 models: - Part Wave - Part Block - Part Funnel With Part Funnel as the base. --- Part Wave: - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [0, 12] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [8, 18] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [13, 23] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [18, 32] --- Part Block: - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [0, 15] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [8, 23] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [16, 32] --- Part Funnel: - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [0, 15] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [14, 14] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [13, 13] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [12, 12] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [11, 11] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [10, 10] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [9, 9] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [8, 23] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [22, 22] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [21, 21] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [20, 20] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [19, 19] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [18, 18] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [17, 17] - sources: - model: NousResearch/Meta-Llama-3-8B-Instruct layer_range: [16, 32]