Mistral
Collection
MistralAI-based models
•
689 items
•
Updated
•
1
merge
This is a merge of pre-trained language models created using mergekit.
Merge Method
This model was merged using the TIES merge method using unsloth/Mistral-Small-24B-Base-2501 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: unsloth/Mistral-Small-24B-Base-2501
#no parameters necessary for base model
- model: SicariusSicariiStuff/Redemption_Wind_24B
parameters:
density: 0.5
weight: 0.5
- model: cognitivecomputations/Dolphin3.0-R1-Mistral-24B
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: unsloth/Mistral-Small-24B-Base-2501
parameters:
normalize: false
int8_mask: true
dtype: float16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 32.79 |
| IFEval (0-Shot) | 40.29 |
| BBH (3-Shot) | 46.28 |
| MATH Lvl 5 (4-Shot) | 41.01 |
| GPQA (0-shot) | 12.98 |
| MuSR (0-shot) | 17.17 |
| MMLU-PRO (5-shot) | 39.00 |
- Downloads last month
- 50
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Triangle104/Mistral-Redemption-Arc
Merge model
this model
Collections including Triangle104/Mistral-Redemption-Arc
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard40.290
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard46.280
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard41.010
- acc_norm on GPQA (0-shot)Open LLM Leaderboard12.980
- acc_norm on MuSR (0-shot)Open LLM Leaderboard17.170
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard39.000