rizla54 / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
d877662 verified
|
raw
history blame
3.74 kB
metadata
license: cc-by-nc-2.0
tags:
  - mergekit
  - merge
base_model: []
model-index:
  - name: rizla54
    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: 58.19
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla54
          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: 78.74
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla54
          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: 61.29
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla54
          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: 53.26
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla54
          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: 76.8
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla54
          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: 20.62
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla54
          name: Open LLM Leaderboard

This is an experimental model that I made by merging two Llama2 70b models and gluing them together with the mergekit of llama70b. The mergekit is a tool that lets me mix and match different models into one big model, keeping all the smarts and skills of the original models. The llama70b is a huge language model that can make words for all kinds of things and ways, based on the GPT-4 thingy.

The merged model has 54 billion thingamajigs and was made trained on 640GB of vram cluster

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 58.15
AI2 Reasoning Challenge (25-Shot) 58.19
HellaSwag (10-Shot) 78.74
MMLU (5-Shot) 61.29
TruthfulQA (0-shot) 53.26
Winogrande (5-shot) 76.80
GSM8k (5-shot) 20.62