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 ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.3 as a base.
Models Merged
The following models were included in the merge:
- grimjim/magnum-twilight-12b
- Nohobby/MN-12B-Siskin-v0.2
- RozGrov/NemoDori-v0.2.2-12B-MN-ties
- spow12/ChatWaifu_v1.4
- GalrionSoftworks/Canidori-12B-v1
Configuration
The following YAML configuration was used to produce this model:
models:
- model: Nohobby/MN-12B-Siskin-v0.2
- model: spow12/ChatWaifu_v1.4
- model: grimjim/magnum-twilight-12b
- model: RozGrov/NemoDori-v0.2.2-12B-MN-ties
- model: GalrionSoftworks/Canidori-12B-v1
merge_method: model_stock
base_model: ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.3
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 18.16 |
| IFEval (0-Shot) | 30.53 |
| BBH (3-Shot) | 34.22 |
| MATH Lvl 5 (4-Shot) | 8.69 |
| GPQA (0-shot) | 2.13 |
| MuSR (0-shot) | 10.91 |
| MMLU-PRO (5-shot) | 22.51 |
- Downloads last month
- 10
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 djuna/MN-Chinofun-12B-3
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard30.530
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard34.220
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard8.690
- acc_norm on GPQA (0-shot)Open LLM Leaderboard2.130
- acc_norm on MuSR (0-shot)Open LLM Leaderboard10.910
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard22.510