README.md

---
library_name: transformers
tags:
- mergekit
- merge
base_model:
- Triangle104/Q2.5-Humane-RP
- EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
model-index:
- name: Q2.5-EvaHumane-RP
  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: 36.76
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-EvaHumane-RP
      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: 33.76
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-EvaHumane-RP
      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: 27.19
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-EvaHumane-RP
      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: 9.17
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-EvaHumane-RP
      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: 11.39
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-EvaHumane-RP
      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: 37.92
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Q2.5-EvaHumane-RP
      name: Open LLM Leaderboard
---
# Merge

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

Quant: https://huggingface.co/Triangle104/Q2.5-EvaHumane-RP-Q4_K_M-GGUF

## Merge Details

Addition of EVA-Qwen Model to try to broaden RP abilities.

### Merge Method

This model was merged using the SLERP merge method.

### Models Merged

The following models were included in the merge:
* [Triangle104/Q2.5-Humane-RP](https://huggingface.co/Triangle104/Q2.5-Humane-RP)
* [EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: Triangle104/Q2.5-Humane-RP
  - model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
merge_method: slerp
base_model: Triangle104/Q2.5-Humane-RP
dtype: bfloat16
parameters:
  t: [0, 0.5, 0.75, 1, 0.75, 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-EvaHumane-RP-details)

|      Metric       |Value|
|-------------------|----:|
|Avg.               |26.03|
|IFEval (0-Shot)    |36.76|
|BBH (3-Shot)       |33.76|
|MATH Lvl 5 (4-Shot)|27.19|
|GPQA (0-shot)      | 9.17|
|MuSR (0-shot)      |11.39|
|MMLU-PRO (5-shot)  |37.92|