README.md

metadata

license: cc-by-4.0
language:
  - en
base_model:
  - mistralai/Mistral-7B-v0.1
  - SanjiWatsuki/Kunoichi-7B
  - SanjiWatsuki/Silicon-Maid-7B
  - KatyTheCutie/LemonadeRP-4.5.3
  - Sao10K/Fimbulvetr-11B-v2
library_name: transformers
tags:
  - mergekit
  - merge
  - mistral
  - text-generation
  - roleplay
model-index:
  - name: Smart-Lemon-Cookie-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: 69.62
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FallenMerick/Chunky-Lemon-Cookie-11B
          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: 86.55
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FallenMerick/Chunky-Lemon-Cookie-11B
          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: 65.35
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FallenMerick/Chunky-Lemon-Cookie-11B
          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: 61.59
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FallenMerick/Chunky-Lemon-Cookie-11B
          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: 79.79
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FallenMerick/Chunky-Lemon-Cookie-11B
          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: 58.45
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FallenMerick/Chunky-Lemon-Cookie-11B
          name: Open LLM Leaderboard

Exllamav2 quant (exl2 / 2.2 bpw) made with ExLlamaV2 v0.1.3

Other EXL2 quants:

Quant	Model Size	lm_head
2.2	3126 MB	6
2.5	3469 MB	6
3.0	4092 MB	6
3.5	4717 MB	6
3.75	5029 MB	6
4.0	5341 MB	6
4.25	5653 MB	6
5.0	6589 MB	6
6.0	7862 MB	8
6.5	8467 MB	8
8.0	9713 MB	8

Chunky-Lemon-Cookie-11B

This is a merge of pre-trained language models created using mergekit.

GGUF quants:

• https://huggingface.co/backyardai/Chunky-Lemon-Cookie-11B-GGUF
• https://huggingface.co/mradermacher/Chunky-Lemon-Cookie-11B-GGUF

Merge Details

Merge Method

This model was merged using the following methods:

• passthrough
• task arithmetic

Models Merged

The following models were included in the merge:

• SanjiWatsuki/Kunoichi-7B
• SanjiWatsuki/Silicon-Maid-7B
• KatyTheCutie/LemonadeRP-4.5.3
• Sao10K/Fimbulvetr-11B-v2
• mistralai/Mistral-7B-v0.1

Configuration

The following YAML configurations were used to produce this model:

slices:
  - sources:
    - model: mistralai/Mistral-7B-v0.1
      layer_range: [0, 24]
  - sources:
    - model: mistralai/Mistral-7B-v0.1
      layer_range: [8, 32]
merge_method: passthrough
dtype: float16
name: Mistral-11B

---

slices:
  - sources:
    - model: SanjiWatsuki/Kunoichi-7B
      layer_range: [0, 24]
  - sources:
    - model: SanjiWatsuki/Silicon-Maid-7B
      layer_range: [8, 24]
  - sources:
    - model: KatyTheCutie/LemonadeRP-4.5.3
      layer_range: [24, 32]
merge_method: passthrough
dtype: float16
name: Big-Lemon-Cookie-11B

---

models:
  - model: Big-Lemon-Cookie-11B
    parameters:
      weight: 0.85
  - model: Sao10K/Fimbulvetr-11B-v2
    parameters:
      weight: 0.15
merge_method: task_arithmetic
base_model: Mistral-11B
dtype: float16
name: Chunky-Lemon-Cookie-11B

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	70.23
AI2 Reasoning Challenge (25-Shot)	69.62
HellaSwag (10-Shot)	86.55
MMLU (5-Shot)	65.35
TruthfulQA (0-shot)	61.59
Winogrande (5-shot)	79.79
GSM8k (5-shot)	58.45