README.md

---
library_name: transformers
tags:
- mergekit
- merge
base_model:
- nbeerbower/mistral-nemo-gutenberg-12B-v3
- nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
- nbeerbower/mistral-nemo-gutenberg-12B-v4
- nbeerbower/mistral-nemo-bophades-12B
model-index:
- name: Stella-mistral-nemo-12B-v2
 results:
 - task:
 type: text-generation
 name: Text Generation
 dataset:
 name: IFEval (0-Shot)
 type: HuggingFaceH4/ifeval
 args:
 num_few_shot: 0
 metrics:
 - type: inst_level_strict_acc and prompt_level_strict_acc
 value: 32.74
 name: strict accuracy
 source:
 url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Stella-mistral-nemo-12B-v2
 name: Open LLM Leaderboard
 - task:
 type: text-generation
 name: Text Generation
 dataset:
 name: BBH (3-Shot)
 type: BBH
 args:
 num_few_shot: 3
 metrics:
 - type: acc_norm
 value: 35.36
 name: normalized accuracy
 source:
 url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Stella-mistral-nemo-12B-v2
 name: Open LLM Leaderboard
 - task:
 type: text-generation
 name: Text Generation
 dataset:
 name: MATH Lvl 5 (4-Shot)
 type: hendrycks/competition_math
 args:
 num_few_shot: 4
 metrics:
 - type: exact_match
 value: 10.42
 name: exact match
 source:
 url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Stella-mistral-nemo-12B-v2
 name: Open LLM Leaderboard
 - task:
 type: text-generation
 name: Text Generation
 dataset:
 name: GPQA (0-shot)
 type: Idavidrein/gpqa
 args:
 num_few_shot: 0
 metrics:
 - type: acc_norm
 value: 10.96
 name: acc_norm
 source:
 url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Stella-mistral-nemo-12B-v2
 name: Open LLM Leaderboard
 - task:
 type: text-generation
 name: Text Generation
 dataset:
 name: MuSR (0-shot)
 type: TAUR-Lab/MuSR
 args:
 num_few_shot: 0
 metrics:
 - type: acc_norm
 value: 14.43
 name: acc_norm
 source:
 url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Stella-mistral-nemo-12B-v2
 name: Open LLM Leaderboard
 - task:
 type: text-generation
 name: Text Generation
 dataset:
 name: MMLU-PRO (5-shot)
 type: TIGER-Lab/MMLU-Pro
 config: main
 split: test
 args:
 num_few_shot: 5
 metrics:
 - type: acc
 value: 29.83
 name: accuracy
 source:
 url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Stella-mistral-nemo-12B-v2
 name: Open LLM Leaderboard
---
# Stella-mistral-nemo-12B-v2

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [nbeerbower/mistral-nemo-bophades-12B](https://huggingface.co/nbeerbower/mistral-nemo-bophades-12B) as a base.

### Models Merged

The following models were included in the merge:
* [nbeerbower/mistral-nemo-gutenberg-12B-v3](https://huggingface.co/nbeerbower/mistral-nemo-gutenberg-12B-v3)
* [nbeerbower/Lyra-Gutenberg-mistral-nemo-12B](https://huggingface.co/nbeerbower/Lyra-Gutenberg-mistral-nemo-12B)
* [nbeerbower/mistral-nemo-gutenberg-12B-v4](https://huggingface.co/nbeerbower/mistral-nemo-gutenberg-12B-v4)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
 - model: nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
 - model: nbeerbower/mistral-nemo-gutenberg-12B-v4
 - model: nbeerbower/mistral-nemo-gutenberg-12B-v3
merge_method: model_stock
base_model: nbeerbower/mistral-nemo-bophades-12B
dtype: bfloat16


```

# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_nbeerbower__Stella-mistral-nemo-12B-v2)

| Metric |Value|
|-------------------|----:|
|Avg. |22.29|
|IFEval (0-Shot) |32.74|
|BBH (3-Shot) |35.36|
|MATH Lvl 5 (4-Shot)|10.42|
|GPQA (0-shot) |10.96|
|MuSR (0-shot) |14.43|
|MMLU-PRO (5-shot) |29.83|