---
language:
- en
license: mit
tags:
- dare
- super mario merge
- pytorch
- mistral
- merge
pipeline_tag: text-generation
inference: false
model-index:
- name: mistral-megamerge-dare-7b
  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: 55.29
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/mistral-megamerge-dare-7b
      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: 70.48
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/mistral-megamerge-dare-7b
      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: 43.05
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/mistral-megamerge-dare-7b
      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: 51.08
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/mistral-megamerge-dare-7b
      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: 67.09
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/mistral-megamerge-dare-7b
      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: 6.6
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/mistral-megamerge-dare-7b
      name: Open LLM Leaderboard
---


# mistral 7b mega merge

This model was merged using [https://github.com/martyn/safetensors-merge-supermario](https://github.com/martyn/safetensors-merge-supermario) with hyperparams `p=0.12` and `lambda=2.1`.

The first entry is the base model:

```
mistralai/Mistral-7B-Instruct-v0.2
uukuguy/speechless-code-mistral-7b-v1.0
AIDC-ai-business/Marcoroni-7B-v3
Weyaxi/Seraph-7B
rwitz/dec10
Intel/neural-chat-7b-v3-3
rwitz/go-bruins-v2
```

To merge your own model:
```
python hf_merge.py to_merge_7b.txt mistral_7b_0.2_merge -p 0.12 -lambda 2.1
```
# [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_martyn__mistral-megamerge-dare-7b)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |48.93|
|AI2 Reasoning Challenge (25-Shot)|55.29|
|HellaSwag (10-Shot)              |70.48|
|MMLU (5-Shot)                    |43.05|
|TruthfulQA (0-shot)              |51.08|
|Winogrande (5-shot)              |67.09|
|GSM8k (5-shot)                   | 6.60|