---
license: apache-2.0
tags:
- merge
- mergekit
- ShinojiResearch/Senku-70B-Full
- 152334H/miqu-1-70b-sf
model-index:
- name: ECE-TW3-JRGL-V1
  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: 55.35
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V1
      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: 46.7
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V1
      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: 11.86
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V1
      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: 12.98
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V1
      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: 17.46
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V1
      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: 35.79
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V1
      name: Open LLM Leaderboard
---

# ECE-TW3-JRGL-V1

## This model has been produced by :

- [Louis Garcia](https://www.linkedin.com/in/louis-garcia-profil/), engineering student at [French Engineering School ECE](https://www.ece.fr/en/)
- [Matthieu Jollard](https://www.linkedin.com/in/matthieu-jollard/), engineering student at [French Engineering School ECE](https://www.ece.fr/en/)

## Under the supervision of :

- [Andre-Louis Rochet](https://www.linkedin.com/in/andrelouisrochet/), Lecturer at ECE & Co-Founder of [TW3 Partners](https://tw3partners.fr/)
- [Paul Lemaistre](https://www.linkedin.com/in/paul-lemaistre/), CTO of [TW3 Partners](https://tw3partners.fr/)

## With the contribution of :

- ECE engineering school as sponsor and financial contributor
- RunPod as financial contributor

## About ECE
>_**ECE**, a multi-program, multi-campus, and multi-sector engineering school specializing in digital engineering,
>  trains engineers and technology experts for the 21st century, capable of meeting the challenges of the dual digital and sustainable development revolutions.
>[French Engineering School ECE](https://www.ece.fr/en/)_
## Description

ECE-TW3-JRGL-V1 is a merge of the following models using **[mergekit](https://github.com/cg123/mergekit)**:

* [ShinojiResearch/Senku-70B-Full](https://huggingface.co/ShinojiResearch/Senku-70B-Full)
* [152334H/miqu-1-70b-sf](https://huggingface.co/152334H/miqu-1-70b-sf)

```yaml
slices:
  - sources:
      - model: ShinojiResearch/Senku-70B-Full
        layer_range: [0, 80]
      - model: 152334H/miqu-1-70b-sf
        layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: float16
```

## Results

- ECE-TW3-JRGL-v1 scores 83.07 on [EQ-Bench V2](https://eqbench.com/index.html)

---
@misc{paech2023eqbench,
	title={EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models},
	author={Samuel J. Paech},
	year={2023},
	eprint={2312.06281},
	archivePrefix={arXiv},
	primaryClass={cs.CL}
}
---

# [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_paloalma__ECE-TW3-JRGL-V1)

|      Metric       |Value|
|-------------------|----:|
|Avg.               |30.02|
|IFEval (0-Shot)    |55.35|
|BBH (3-Shot)       |46.70|
|MATH Lvl 5 (4-Shot)|11.86|
|GPQA (0-shot)      |12.98|
|MuSR (0-shot)      |17.46|
|MMLU-PRO (5-shot)  |35.79|