Gemma
Collection
Google-based models
•
174 items
•
Updated
•
1
Merge
This is a merge of pre-trained language models created using mergekit.
Merge Method
This model was merged using the Model Stock merge method using TheDrummer/Gemmasutra-9B-v1.1 as a base.
Models Merged
The following models were included in the merge:
- DavidAU/Gemma-The-Writer-Mighty-Sword-9B
- Rombo-Org/Rombo-LLM-V2.7-gemma-2-9b
- anthracite-org/magnum-v4-9b
- nbeerbower/Gemma2-Gutenberg-Doppel-9B
- allura-org/G2-9B-Aletheia-v1
Configuration
The following YAML configuration was used to produce this model:
models:
- model: TheDrummer/Gemmasutra-9B-v1.1
- model: Rombo-Org/Rombo-LLM-V2.7-gemma-2-9b
- model: allura-org/G2-9B-Aletheia-v1
- model: anthracite-org/magnum-v4-9b
- model: nbeerbower/Gemma2-Gutenberg-Doppel-9B
- model: DavidAU/Gemma-The-Writer-Mighty-Sword-9B
merge_method: model_stock
base_model: TheDrummer/Gemmasutra-9B-v1.1
parameters:
normalize: true
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 21.58 |
| IFEval (0-Shot) | 15.82 |
| BBH (3-Shot) | 43.62 |
| MATH Lvl 5 (4-Shot) | 2.79 |
| GPQA (0-shot) | 13.76 |
| MuSR (0-shot) | 17.23 |
| MMLU-PRO (5-shot) | 36.24 |
- Downloads last month
- 36
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for Triangle104/Gemmadevi-Stock-10B
Merge model
this model
Spaces using Triangle104/Gemmadevi-Stock-10B 3
Collections including Triangle104/Gemmadevi-Stock-10B
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard15.820
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard43.620
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard2.790
- acc_norm on GPQA (0-shot)Open LLM Leaderboard13.760
- acc_norm on MuSR (0-shot)Open LLM Leaderboard17.230
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard36.240