merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the passthrough merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: rombodawg/Rombos-LLM-V2.6-Qwen-14b
layer_range: [0, 8]
- sources:
- model: rombodawg/Rombos-LLM-V2.6-Qwen-14b
layer_range: [8, 24]
parameters:
scale:
- filter: q_proj
value: 0.919
- filter: k_proj
value: 0.919
- value: 1.0
- sources:
- model: rombodawg/Rombos-LLM-V2.6-Qwen-14b
layer_range: [16, 24]
parameters:
scale:
- filter: q_proj
value: 0.7
- filter: k_proj
value: 0.7
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- model: rombodawg/Rombos-LLM-V2.6-Qwen-14b
layer_range: [16, 32]
parameters:
scale:
- filter: q_proj
value: 0.919
- filter: k_proj
value: 0.919
- value: 1.0
- sources:
- model: rombodawg/Rombos-LLM-V2.6-Qwen-14b
layer_range: [32, 40]
merge_method: passthrough
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 18.13 |
| IFEval (0-Shot) | 18.69 |
| BBH (3-Shot) | 44.27 |
| MATH Lvl 5 (4-Shot) | 0.00 |
| GPQA (0-shot) | 2.68 |
| MuSR (0-shot) | 5.53 |
| MMLU-PRO (5-shot) | 37.57 |