README.md

---
license: cc-by-nc-4.0
library_name: transformers
tags:
- mergekit
- merge
base_model:
- grimjim/zephyr-beta-wizardLM-2-merge-7B
- core-3/kuno-royale-v2-7b
pipeline_tag: text-generation
model-index:
- name: grimjim/zephyr-wizard-kuno-royale-BF16-merge-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: 68.69
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/zephyr-wizard-kuno-royale-BF16-merge-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: 86.87
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/zephyr-wizard-kuno-royale-BF16-merge-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: 64.87
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/zephyr-wizard-kuno-royale-BF16-merge-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: 65.47
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/zephyr-wizard-kuno-royale-BF16-merge-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: 80.03
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/zephyr-wizard-kuno-royale-BF16-merge-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: 63.31
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/zephyr-wizard-kuno-royale-BF16-merge-7B
      name: Open LLM Leaderboard
---
# zephyr-wizard-kuno-royale-BF16-merge-7B

This is an experimental merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). All source model weights are BF16, avoiding issues arising from mixed-precision merges.

Although the zephyr beta and WizardLM 2 7B models are touted as SOTA and can generate varied prose compared to base Mistral v0.1, their relatively mediocre benchmarks under GSM-8K suggests only average reasoning capability in one-shot narrative text completion. The kuno-royale-v2 model was selected for merger because of its higher GSM-8K rating.

Native prompt format is Alpaca, although at least one of the prior models was fine-tuned to Vicuna.

Tested lightly with ChatML instruct prompts, temperature 1, and minP 0.02.

## Merge Details
### Merge Method

This model was merged using the SLERP merge method.

### Models Merged

The following models were included in the merge:
* [grimjim/zephyr-beta-wizardLM-2-merge-7B](https://huggingface.co/grimjim/zephyr-beta-wizardLM-2-merge-7B)
* [core-3/kuno-royale-v2-7b](https://huggingface.co/core-3/kuno-royale-v2-7b)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
slices:
  - sources:
    - model: grimjim/zephyr-beta-wizardLM-2-merge-7B
      layer_range: [0,32]
    - model: core-3/kuno-royale-v2-7b
      layer_range: [0,32]
merge_method: slerp
base_model: grimjim/zephyr-beta-wizardLM-2-merge-7B
parameters:
  t:
    - value: 0.5
dtype: bfloat16

```

# [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_grimjim__zephyr-wizard-kuno-royale-BF16-merge-7B)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |71.54|
|AI2 Reasoning Challenge (25-Shot)|68.69|
|HellaSwag (10-Shot)              |86.87|
|MMLU (5-Shot)                    |64.87|
|TruthfulQA (0-shot)              |65.47|
|Winogrande (5-shot)              |80.03|
|GSM8k (5-shot)                   |63.31|