Built With Qwen
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the TIES merge method using Qwen/Qwen2.5-72B as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: Qwen/Qwen2.5-72B-Instruct
parameters:
weight: 1
density: 1
merge_method: ties
base_model: Qwen/Qwen2.5-72B
parameters:
weight: 1
density: 1
normalize: true
int8_mask: true
dtype: float16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 46.58 |
| IFEval (0-Shot) | 71.40 |
| BBH (3-Shot) | 61.10 |
| MATH Lvl 5 (4-Shot) | 52.42 |
| GPQA (0-shot) | 21.92 |
| MuSR (0-shot) | 18.12 |
| MMLU-PRO (5-shot) | 54.51 |
- Downloads last month
- 2,215
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Sakalti/ultiima-72B
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard71.400
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard61.100
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard52.420
- acc_norm on GPQA (0-shot)Open LLM Leaderboard21.920
- acc_norm on MuSR (0-shot)Open LLM Leaderboard18.120
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard54.510