README.md

---
license: llama3.2
library_name: transformers
tags:
- mergekit
- merge
base_model:
- KingNish/Reasoning-Llama-1b-v0.1
- zztheaven/Llama-3.2-1B-Instruct-Open-R1-GRPO
- prithivMLmods/Bellatrix-Tiny-1B-R1
model-index:
- name: Llama_3.2_1b_OpenTree_R1_0.1
  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: 53.66
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_OpenTree_R1_0.1
      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: 6.21
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_OpenTree_R1_0.1
      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: 4.76
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_OpenTree_R1_0.1
      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: 0.34
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_OpenTree_R1_0.1
      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: 1.6
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_OpenTree_R1_0.1
      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: 7.5
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_1b_OpenTree_R1_0.1
      name: Open LLM Leaderboard
---
# merge

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 [zztheaven/Llama-3.2-1B-Instruct-Open-R1-GRPO](https://huggingface.co/zztheaven/Llama-3.2-1B-Instruct-Open-R1-GRPO) as a base.

### Models Merged

The following models were included in the merge:
* [KingNish/Reasoning-Llama-1b-v0.1](https://huggingface.co/KingNish/Reasoning-Llama-1b-v0.1)
* [prithivMLmods/Bellatrix-Tiny-1B-R1](https://huggingface.co/prithivMLmods/Bellatrix-Tiny-1B-R1)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: model_stock
models:
  - model: KingNish/Reasoning-Llama-1b-v0.1
    parameters:
      weight: 1.0
  - model: prithivMLmods/Bellatrix-Tiny-1B-R1
    parameters:
      weight: 1.0
base_model: zztheaven/Llama-3.2-1B-Instruct-Open-R1-GRPO
dtype: bfloat16
normalize: true
```
# [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/Nexesenex__Llama_3.2_1b_OpenTree_R1_0.1-details)

|      Metric       |Value|
|-------------------|----:|
|Avg.               |12.34|
|IFEval (0-Shot)    |53.66|
|BBH (3-Shot)       | 6.21|
|MATH Lvl 5 (4-Shot)| 4.76|
|GPQA (0-shot)      | 0.34|
|MuSR (0-shot)      | 1.60|
|MMLU-PRO (5-shot)  | 7.50|