| | --- |
| | base_model: |
| | - Qwen/Qwen2.5-Math-72B |
| | - Qwen/Qwen2.5-72B-Instruct |
| | library_name: transformers |
| | tags: |
| | - mergekit |
| | - merge |
| | license: other |
| | --- |
| | |
| | ## Qwen2.5-142B-Doubled72B-Math-Instruct (Mergekit-Merge) by Solshine (Caleb DeLeeuw) |
| |  |
| |
|
| | # merge |
| |
|
| | This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
| |
|
| | # License |
| |
|
| | Hippocratic License 3.0 + Ecocide module, + Extractive Industries module, + Copyleft |
| | [](https://firstdonoharm.dev/version/3/0/cl-eco-extr.html) |
| | https://firstdonoharm.dev/version/3/0/cl-eco-extr.txt |
| |
|
| |
|
| | ## Merge Details |
| | ### Merge Method |
| |
|
| | This model was merged using the passthrough merge method. Every layer is doubled in order, from Qwen/Qwen2.5-72B-Instruct and Qwen/Qwen2.5-Math-72B, alternating which model is adding a layer and the MLP layers + 2 output layers only taken from the instruct model, creating 142B parameters. No additional fine-tune has been done in this merged model. |
| |
|
| | ### Models Merged |
| |
|
| | The following models were included in the merge: |
| | * [Qwen/Qwen2.5-Math-72B](https://huggingface.co/Qwen/Qwen2.5-Math-72B) |
| | * [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct) |
| |
|
| | ### Configuration |
| |
|
| | The following YAML configuration was used to produce this model: |
| |
|
| | ```yaml |
| | slices: |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [0, 1] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [0, 1] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [1, 2] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [1, 2] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [2, 3] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [2, 3] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [3, 4] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [3, 4] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [4, 5] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [4, 5] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [5, 6] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [5, 6] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [6, 7] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [6, 7] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [7, 8] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [7, 8] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [8, 9] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [8, 9] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [9, 10] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [9, 10] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [10, 11] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [10, 11] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [11, 12] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [11, 12] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [12, 13] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [12, 13] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [13, 14] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [13, 14] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [14, 15] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [14, 15] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [15, 16] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [15, 16] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [16, 17] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [16, 17] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [17, 18] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [17, 18] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [18, 19] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [18, 19] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [19, 20] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [19, 20] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [20, 21] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [20, 21] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [21, 22] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [21, 22] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [22, 23] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [22, 23] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [23, 24] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [23, 24] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [24, 25] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [24, 25] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [25, 26] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [25, 26] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [26, 27] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [26, 27] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [27, 28] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [27, 28] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [28, 29] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [28, 29] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [29, 30] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [29, 30] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [30, 31] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [30, 31] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [31, 32] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [31, 32] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [32, 33] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [32, 33] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [33, 34] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [33, 34] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [34, 35] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [34, 35] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [35, 36] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [35, 36] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [36, 37] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [36, 37] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [37, 38] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [37, 38] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [38, 39] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [38, 39] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [39, 40] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [39, 40] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [40, 41] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [40, 41] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [41, 42] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [41, 42] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [42, 43] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [42, 43] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [43, 44] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [43, 44] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [44, 45] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [44, 45] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [45, 46] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [45, 46] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [46, 47] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [46, 47] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [47, 48] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [47, 48] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [48, 49] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [48, 49] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [49, 50] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [49, 50] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [50, 51] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [50, 51] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [51, 52] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [51, 52] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [52, 53] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [52, 53] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [53, 54] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [53, 54] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [54, 55] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [54, 55] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [55, 56] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [55, 56] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [56, 57] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [56, 57] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [57, 58] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [57, 58] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [58, 59] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [58, 59] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [59, 60] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [59, 60] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [60, 61] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [60, 61] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [61, 62] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [61, 62] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [62, 63] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [62, 63] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [63, 64] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [63, 64] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [64, 65] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [64, 65] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [65, 66] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [65, 66] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [66, 67] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [66, 67] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [67, 68] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [67, 68] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [68, 69] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [68, 69] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [69, 70] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [69, 70] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [70, 71] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [70, 71] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [71, 72] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [71, 72] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [72, 73] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [72, 73] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [73, 74] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [73, 74] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [74, 75] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [74, 75] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [75, 76] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [75, 76] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [76, 77] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [76, 77] |
| | - sources: |
| | - model: Qwen/Qwen2.5-Math-72B |
| | layer_range: [77, 78] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [77, 78] |
| | - sources: |
| | - model: Qwen/Qwen2.5-72B-Instruct |
| | layer_range: [77, 80] |
| | merge_method: passthrough |
| | dtype: float16 |
| | ``` |
