README.md

---
base_model:
- Qwen/Qwen2.5-14B-Instruct
- prithivMLmods/Calcium-Opus-14B-Elite
- prithivMLmods/QwQ-LCoT-14B-Conversational
library_name: transformers
tags:
- mergekit
- merge
model-index:
- name: Calcium-Opus-14B-Merge
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: wis-k/instruction-following-eval
      split: train
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 49.49
      name: averaged accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Merge
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: SaylorTwift/bbh
      split: test
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 46.77
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Merge
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: lighteval/MATH-Hard
      split: test
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 33.08
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Merge
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      split: train
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 16.11
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Merge
      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: 20.93
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Merge
      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: 48.4
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FCalcium-Opus-14B-Merge
      name: Open LLM Leaderboard
---
# **Calcium-Opus-14B-Merge**

Calcium-Opus-14B-Merge is based on the Qwen 2.5 14B modality architecture, designed to enhance the reasoning capabilities of 14B-parameter models. These models have proven effective in context understanding, reasoning, and mathematical problem-solving. It has been fine-tuned using a long chain-of-thought reasoning model and specialized datasets, with a focus on chain-of-thought (CoT) reasoning for problem-solving. This model is optimized for tasks requiring logical reasoning, detailed explanations, and multi-step problem-solving, making it ideal for applications such as instruction-following, text generation, and complex reasoning tasks.

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

### Merge Method

This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) as a base.

### Models Merged

The following models were included in the merge:
* [prithivMLmods/Calcium-Opus-14B-Elite](https://huggingface.co/prithivMLmods/Calcium-Opus-14B-Elite)
* [prithivMLmods/QwQ-LCoT-14B-Conversational](https://huggingface.co/prithivMLmods/QwQ-LCoT-14B-Conversational)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: prithivMLmods/Calcium-Opus-14B-Elite
  - model: prithivMLmods/QwQ-LCoT-14B-Conversational
merge_method: model_stock
base_model: Qwen/Qwen2.5-14B-Instruct
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16
tokenizer_source: "Qwen/Qwen2.5-14B-Instruct"
```

# [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/prithivMLmods__Calcium-Opus-14B-Merge-details)!
Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=prithivMLmods%2FCalcium-Opus-14B-Merge&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!

|      Metric       |Value (%)|
|-------------------|--------:|
|**Average**        |    35.80|
|IFEval (0-Shot)    |    49.49|
|BBH (3-Shot)       |    46.77|
|MATH Lvl 5 (4-Shot)|    33.08|
|GPQA (0-shot)      |    16.11|
|MuSR (0-shot)      |    20.93|
|MMLU-PRO (5-shot)  |    48.40|