README.md

---
license: cc-by-nc-4.0
library_name: transformers
tags:
- mergekit
- merge
- alpaca
- mistral
- not-for-all-audiences
- nsfw
base_model:
- icefog72/Kunokukulemonchini-32k-7b
- icefog72/Mixtral_AI_Cyber_3.m1-BigL
- grimjim/kukulemon-32K-7B
- LeroyDyer/Mixtral_AI_Cyber_3.m1
- Nitral-AI/Kunocchini-7b-128k-test
- Undi95/BigL-7B
model-index:
- name: IceLemonTeaRP-32k-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: 67.66
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-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: 86.53
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-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: 64.51
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-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: 61.76
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-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: 79.72
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-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: 62.4
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-7b
      name: Open LLM Leaderboard
---
# IceLemonTeaRP-32k-7b

![image/png](https://cdn-uploads.huggingface.co/production/uploads/63407b719dbfe0d48b2d763b/PSpmU4l79CrdfzbCd-xSf.png)

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

I would suggest to play with rope_theta in config.json to set between 40000-100000.

## Merge Details

Cooked merge from fresh ingredients to fix [icefog72/IceTeaRP-7b](https://huggingface.co/icefog72/IceTeaRP-7b) repetition problems.

Prompt template: Alpaca, maybe ChatML

* measurement.json for quanting exl2 included. 

- [IceLemonTeaRP-32k-7b-4.0bpw-h6-exl2](https://huggingface.co/icefog72/IceLemonTeaRP-32k-7b-4.0bpw-h6-exl2)
- [IceLemonTeaRP-32k-7b-4.2bpw-h6-exl2](https://huggingface.co/icefog72/IceLemonTeaRP-32k-7b-4.2bpw-h6-exl2)
- [IceLemonTeaRP-32k-7b-6.5bpw-h6-exl2](https://huggingface.co/icefog72/IceLemonTeaRP-32k-7b-6.5bpw-h6-exl2)
- [IceLemonTeaRP-32k-7b-8.0bpw-h6-exl2](https://huggingface.co/icefog72/IceLemonTeaRP-32k-7b-8.0bpw-h6-exl2)

Thanks for 
- [mradermacher/IceTeaRP-7b-GGUF](https://huggingface.co/mradermacher/IceLemonTeaRP-32k-7b-GGUF)
- [Natkituwu/IceLemonTeaRP-32k-7b-7.1bpw-exl2](https://huggingface.co/Natkituwu/IceLemonTeaRP-32k-7b-7.1bpw-exl2)

### Merge Method

This model was merged using the SLERP merge method.

### Models Merged

The following models were included in the merge:
* icefog72/Kunokukulemonchini-32k-7b
  * [grimjim/kukulemon-32K-7B](https://huggingface.co/grimjim/kukulemon-32K-7B)
  * [Nitral-AI/Kunocchini-7b-128k-test](https://huggingface.co/Nitral-AI/Kunocchini-7b-128k-test)
* icefog72/Mixtral_AI_Cyber_3.m1-BigL
  * [LeroyDyer/Mixtral_AI_Cyber_3.m1](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_3.m1)
  * [Undi95/BigL-7B](https://huggingface.co/Undi95/BigL-7B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml

slices:
  - sources:
      - model: Mixtral_AI_Cyber_3.m1-BigL
        layer_range: [0, 32]
      - model: Kunokukulemonchini-32k-7b
        layer_range: [0, 32]
merge_method: slerp
base_model: Kunokukulemonchini-32k-7b
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
```

# [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_icefog72__IceLemonTeaRP-32k-7b)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |70.43|
|AI2 Reasoning Challenge (25-Shot)|67.66|
|HellaSwag (10-Shot)              |86.53|
|MMLU (5-Shot)                    |64.51|
|TruthfulQA (0-shot)              |61.76|
|Winogrande (5-shot)              |79.72|
|GSM8k (5-shot)                   |62.40|