merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Model Stock merge method using huihui-ai/Qwen2.5-3B-Instruct-abliterated as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
merge_method: model_stock
models:
- model: huihui-ai/Qwen2.5-Coder-3B-Instruct-abliterated
parameters:
weight: 1.0
- model: huihui-ai/Dria-Agent-a-3B-abliterated
parameters:
weight: 1.0
base_model: huihui-ai/Qwen2.5-3B-Instruct-abliterated
dtype: bfloat16
normalize: true
chat_template: auto
tokenizer:
source: union
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 19.96 |
| IFEval (0-Shot) | 40.12 |
| BBH (3-Shot) | 24.37 |
| MATH Lvl 5 (4-Shot) | 18.05 |
| GPQA (0-shot) | 3.69 |
| MuSR (0-shot) | 12.87 |
| MMLU-PRO (5-shot) | 20.67 |
- Downloads last month
- 40
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Nexesenex/Qwen_2.5_3b_Smarteaz_0.01a
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard40.120
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard24.370
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard18.050
- acc_norm on GPQA (0-shot)Open LLM Leaderboard3.690
- acc_norm on MuSR (0-shot)Open LLM Leaderboard12.870
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard20.670