README.md

---
license: apache-2.0
library_name: transformers
tags:
- mergekit
- merge
base_model:
- Qwen/Qwen2.5-7B-Instruct-1M
- huihui-ai/Qwen2.5-7B-Instruct-1M-abliterated
model-index:
- name: Q2.5-Instruct-1M_Harmony
  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: 60.38
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-Instruct-1M_Harmony
      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: 33.63
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-Instruct-1M_Harmony
      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: 32.1
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-Instruct-1M_Harmony
      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: 9.73
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-Instruct-1M_Harmony
      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: 18.1
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-Instruct-1M_Harmony
      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: 37.4
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-Instruct-1M_Harmony
      name: Open LLM Leaderboard
---
# merge

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 [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.

### Models Merged

The following models were included in the merge:
* [Qwen/Qwen2.5-7B-Instruct-1M](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-1M)
* [huihui-ai/Qwen2.5-7B-Instruct-1M-abliterated](https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-1M-abliterated)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: huihui-ai/Qwen2.5-7B-Instruct-1M-abliterated
  - model: Qwen/Qwen2.5-7B-Instruct-1M
merge_method: slerp
base_model: Qwen/Qwen2.5-7B-Instruct-1M
dtype: bfloat16
parameters:
  t: [0, 0.5, 1, 0.5, 0]

```
# [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/Triangle104__Q2.5-Instruct-1M_Harmony-details)

|      Metric       |Value|
|-------------------|----:|
|Avg.               |31.89|
|IFEval (0-Shot)    |60.38|
|BBH (3-Shot)       |33.63|
|MATH Lvl 5 (4-Shot)|32.10|
|GPQA (0-shot)      | 9.73|
|MuSR (0-shot)      |18.10|
|MMLU-PRO (5-shot)  |37.40|