---
license: cc-by-nc-4.0
tags:
- moe
- merge
- mergekit
base_model:
- mlabonne/AlphaMonarch-7B
- beowolx/CodeNinja-1.0-OpenChat-7B
- SanjiWatsuki/Kunoichi-DPO-v2-7B
- mlabonne/NeuralDaredevil-7B
model-index:
- name: Beyonder-4x7B-random-lora
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 71.25
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aratako/Beyonder-4x7B-random-lora
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 87.4
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aratako/Beyonder-4x7B-random-lora
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 64.78
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aratako/Beyonder-4x7B-random-lora
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 70.49
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aratako/Beyonder-4x7B-random-lora
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 82.16
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aratako/Beyonder-4x7B-random-lora
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 67.4
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aratako/Beyonder-4x7B-random-lora
      name: Open LLM Leaderboard
---

# Beyonder-4x7B-v3-random-lora

The idea was very simple. If heuristic methods for determining gate parameters in mergekit-based MoE models can work well, then perhaps we could obtain a better performing model by fine-tuning only the gate parameters.

This model is an attempt at testing that idea. Unfortunately, the performance degraded slightly, but I am sharing it as an experimental result.

## Model Details

First, I created an MoE model using mergekit with gate_mode=random and the following four models (same as [mlabonne/Beyonder-4x7B-v3](https://huggingface.co/mlabonne/Beyonder-4x7B-v3)):
- [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B)
- [beowolx/CodeNinja-1.0-OpenChat-7B](https://huggingface.co/beowolx/CodeNinja-1.0-OpenChat-7B)
- [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
- [mlabonne/NeuralDaredevil-7](https://huggingface.co/mlabonne/NeuralDaredevil-7B)

Then, I used LoRA to fine-tune only the gate parameters by specifying "gate" in target_modules.
The data used for fine-tuning is as follows. I used the Mistral prompt format.
- 5000 random samples from [llm-jp/oasst1-21k-en](https://huggingface.co/datasets/llm-jp/oasst1-21k-en)
- 5000 random samples from [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k)
- 5000 random samples from [hieunguyenminh/roleplay](https://huggingface.co/datasets/hieunguyenminh/roleplay)
- 5000 random samples from [meta-math/MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA)
- 5000 random samples from [m-a-p/CodeFeedback-Filtered-Instruction](https://huggingface.co/datasets/m-a-p/CodeFeedback-Filtered-Instruction)

The training was conducted on runpod using 4xA6000 GPUs. The main training parameters are as follows:
- lora_r: 128
- lora_alpha: 256
- lora_dropout: 0.05
- lora_target_modules: "gate"
- learning_rate: 3e-4
- num_train_epochs: 5
- batch_size: 64
- max_seq_length: 2048

## Evaluation

The evaluation results show a slight degradation in performance.
Apart from the possibility that this approach may not be effective, other potential causes could be issues with the dataset, training parameters, training setup (such as prompt formatting), and so on.

### Nous ([LLM AutoEval](https://github.com/mlabonne/llm-autoeval))

| Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench |
|---|---:|---:|---:|---:|---:|
| [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B) [📄](https://gist.github.com/mlabonne/1d33c86824b3a11d2308e36db1ba41c1) | 62.74 | 45.37 | 77.01 | 78.39 | 50.2 |
| [mlabonne/Beyonder-4x7B-v3](https://huggingface.co/mlabonne/Beyonder-4x7B-v3) [📄](https://gist.github.com/mlabonne/3740020807e559f7057c32e85ce42d92) | 61.91 | 45.85 | 76.67 | 74.98 | 50.12 |
| [**Aratako/Beyonder-4x7B-v3-random-lora**](https://huggingface.co/Aratako/Beyonder-4x7B-v3-random-lora) [📄](https://gist.github.com/Aratako/f86144312989d69f92c64ea4f25a8bb6) | **60.29** | **45.82** | **76.69** | **69.94** | **48.72** |
| [mlabonne/NeuralDaredevil-7B](https://huggingface.co/mlabonne/NeuralDaredevil-7B) [📄](https://gist.github.com/mlabonne/cbeb077d1df71cb81c78f742f19f4155) | 59.39 | 45.23 | 76.2 | 67.61 | 48.52 |
| [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B) [📄](https://gist.github.com/mlabonne/895ff5171e998abfdf2a41a4f9c84450) | 58.29 | 44.79 | 75.05 | 65.68 | 47.65 |
| [mlabonne/Beyonder-4x7B-v2](https://huggingface.co/mlabonne/Beyonder-4x7B-v2) [📄](https://gist.github.com/mlabonne/f73baa140a510a676242f8a4496d05ca) | 57.13 | 45.29 | 75.95 | 60.86 | 46.4 |
| [beowolx/CodeNinja-1.0-OpenChat-7B](https://huggingface.co/beowolx/CodeNinja-1.0-OpenChat-7B) [📄](https://gist.github.com/mlabonne/08b5280c221fbd7f98eb27561ae902a3) | 50.35 | 39.98 | 71.77 | 48.73 | 40.92 |

### [MT-Bench](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge)

**1-turn**
|Model|Coding|Extraction|Humanities|Math|Reasoning|Roleplay|STEM|Writing|avg_score|
|---|---|---|---|---|---|---|---|---|---|
| [mlabonne/Beyonder-4x7B-v3](https://huggingface.co/mlabonne/Beyonder-4x7B-v3) | 6.7 | 8.3 | 9.7 | 6.7 | 6.3 | 9.3 | 9.7 | 10.0 | 8.33750 |
| [**Aratako/Beyonder-4x7B-v3-random-lora**](https://huggingface.co/Aratako/Beyonder-4x7B-v3-random-lora)  | **6.6** | **8.2** | **9.6** | **6.3** | **6.4** | **8.7** | **9.4** | **9.5** | **8.08750** |
| [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)  | 5.3 | 8.5 | 9.9 | 6.8 | 6.0 | 9.1 | 9.55 | 8.9 | 8.00625 |

![mt-bench-1turn](./mt-bench-1turn.png)

**2-turn**
|Model|Coding|Extraction|Humanities|Math|Reasoning|Roleplay|STEM|Writing|avg_score|
|---|---|---|---|---|---|---|---|---|---|
| [mlabonne/Beyonder-4x7B-v3](https://huggingface.co/mlabonne/Beyonder-4x7B-v3) | 5.4 | 7.6 | 10.0 | 3.5 | 5.5 | 9.0 | 9.6 | 9.1 | 7.46250 |
| [**Aratako/Beyonder-4x7B-v3-random-lora**](https://huggingface.co/Aratako/Beyonder-4x7B-v3-random-lora)  | **5.1** | **8.1** | **9.9** | **4.1** | **3.7** | **8.55** | **9.0** | **7.7** | **7.01875** |
| [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)  | 4.1 | 8.4 | 9.8 | 4.7 | 5.6 | 9.0 | 9.2 | 9.5 | 7.53750 |

![mt-bench-2turn](./mt-bench-2turn.png)
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Aratako__Beyonder-4x7B-random-lora)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |73.91|
|AI2 Reasoning Challenge (25-Shot)|71.25|
|HellaSwag (10-Shot)              |87.40|
|MMLU (5-Shot)                    |64.78|
|TruthfulQA (0-shot)              |70.49|
|Winogrande (5-shot)              |82.16|
|GSM8k (5-shot)                   |67.40|