Merge Models
Collection
Models I merged using mergekit library
•
8 items
•
Updated
•
4
Merged Model
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 gz987/qwen2.5-7b-cabs-v0.3 as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
name: Clarus-7B-v0.2
merge_method: model_stock
base_model: gz987/qwen2.5-7b-cabs-v0.3
tokenizer_source: base
dtype: bfloat16
out_dtype: bfloat16
parameters:
int8_mask: true
normalize: true
rescale: false
models:
- model: gz987/qwen2.5-7b-cabs-v0.4
- model: gz987/qwen2.5-7b-cabs-v0.2
- model: gz987/qwen2.5-7b-cabs-v0.1
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 36.86 |
| IFEval (0-Shot) | 76.79 |
| BBH (3-Shot) | 36.02 |
| MATH Lvl 5 (4-Shot) | 48.56 |
| GPQA (0-shot) | 6.94 |
| MuSR (0-shot) | 15.07 |
| MMLU-PRO (5-shot) | 37.78 |
- Downloads last month
- 23
Model tree for suayptalha/Clarus-7B-v0.2
Merge model
this model
Collection including suayptalha/Clarus-7B-v0.2
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard76.790
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard36.020
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard48.560
- acc_norm on GPQA (0-shot)Open LLM Leaderboard6.940
- acc_norm on MuSR (0-shot)Open LLM Leaderboard15.070
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard37.780