README.md

metadata

license: other
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - NousResearch/Yarn-Mistral-7b-128k
  - Test157t/Kunocchini-1.1-7b
model-index:
  - name: Kunocchini-1.2-7b-longtext
    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: 59.9
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Kunocchini-1.2-7b-longtext
          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: 82.51
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Kunocchini-1.2-7b-longtext
          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: 63.05
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Kunocchini-1.2-7b-longtext
          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: 41.72
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Kunocchini-1.2-7b-longtext
          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: 77.35
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Kunocchini-1.2-7b-longtext
          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: 32.9
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Kunocchini-1.2-7b-longtext
          name: Open LLM Leaderboard

NOTES: This model seems to be overtly confident leading to hallucinations, normalization has seemed to also break the long context chaining. I do not recommend this model.

Thanks to @Epiculous for the dope model/ help with llm backends and support overall.

Id like to also thank @kalomaze for the dope sampler additions to ST.

@SanjiWatsuki Thank you very much for the help, and the model!

Quants Here: Thanks to @Lewdiculus https://huggingface.co/Lewdiculous/Kunocchini-1.2-7b-longtext-GGUF-Imatrix

This model was merged using the DARE TIES.

Models Merged

The following models were included in the merge:

• NousResearch/Yarn-Mistral-7b-128k + Test157t/Kunocchini-1.1-7b

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
base_model: Test157t/Kunocchini-1.1-7b
parameters:
  normalize: true
models:
  - model: NousResearch/Yarn-Mistral-7b-128k
    parameters:
      weight: 1
  - model: Test157t/Kunocchini-1.1-7b
    parameters:
      weight: 1
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	59.57
AI2 Reasoning Challenge (25-Shot)	59.90
HellaSwag (10-Shot)	82.51
MMLU (5-Shot)	63.05
TruthfulQA (0-shot)	41.72
Winogrande (5-shot)	77.35
GSM8k (5-shot)	32.90