leaderboard-pr-bot's picture
Adding Evaluation Results
85d858b verified
|
raw
history blame
4.76 kB
metadata
license: other
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - Test157t/Pasta-Lake-7b
  - Test157t/Prima-LelantaclesV4-7b-16k
model-index:
  - name: Prima-LelantaclesV5-7b
    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: 70.65
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Prima-LelantaclesV5-7b
          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: 87.87
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Prima-LelantaclesV5-7b
          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: 64.52
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Prima-LelantaclesV5-7b
          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: 68.26
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Prima-LelantaclesV5-7b
          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: 82.4
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Prima-LelantaclesV5-7b
          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: 64.82
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Prima-LelantaclesV5-7b
          name: Open LLM Leaderboard

Update: Getting suprisingly good results at 16384 context, which is unexpected given this context pool should remain untouched from other mistral models working around 8192.

image/png

image/jpeg

Thanks to @Lewdiculus for the Quants: https://huggingface.co/Lewdiculous/Prima-LelantaclesV5-7b-GGUF

This model was merged using the DARE TIES merge method.

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
base_model: Test157t/Prima-LelantaclesV4-7b-16k
parameters:
  normalize: true
models:
  - model: Test157t/Pasta-Lake-7b
    parameters:
      weight: 1
  - model: Test157t/Prima-LelantaclesV4-7b-16k
    parameters:
      weight: 1
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 73.09
AI2 Reasoning Challenge (25-Shot) 70.65
HellaSwag (10-Shot) 87.87
MMLU (5-Shot) 64.52
TruthfulQA (0-shot) 68.26
Winogrande (5-shot) 82.40
GSM8k (5-shot) 64.82