leaderboard-pr-bot's picture
Adding Evaluation Results
39189c4 verified
|
raw
history blame
4.8 kB
metadata
language:
  - en
license: llama2
datasets:
  - garage-bAInd/Open-Platypus
  - GAIR/lima
model-index:
  - name: Limarp-Platypus2-13B-QLoRA-0.80-epoch
    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: 60.49
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TFLai/Limarp-Platypus2-13B-QLoRA-0.80-epoch
          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: 82.76
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TFLai/Limarp-Platypus2-13B-QLoRA-0.80-epoch
          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: 56.52
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TFLai/Limarp-Platypus2-13B-QLoRA-0.80-epoch
          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: 44.14
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TFLai/Limarp-Platypus2-13B-QLoRA-0.80-epoch
          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=TFLai/Limarp-Platypus2-13B-QLoRA-0.80-epoch
          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: 6.07
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TFLai/Limarp-Platypus2-13B-QLoRA-0.80-epoch
          name: Open LLM Leaderboard

image/png

Buy Me A Coffee

Limarp-Platypus2-13B-QLoRA-0.80-epoch

Limarp-Platypus2-13B-QLoRA-0.80-epoch is a merge of Oniichat/limarp-13b-merged and Platypus2-13B-QLoRA-0.80-epoch

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 47.74
ARC (25-shot) 60.49
HellaSwag (10-shot) 82.76
MMLU (5-shot) 56.52
TruthfulQA (0-shot) 44.14
Winogrande (5-shot) 76.8
GSM8K (5-shot) 6.07
DROP (3-shot) 7.4

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 54.46
AI2 Reasoning Challenge (25-Shot) 60.49
HellaSwag (10-Shot) 82.76
MMLU (5-Shot) 56.52
TruthfulQA (0-shot) 44.14
Winogrande (5-shot) 76.80
GSM8k (5-shot) 6.07