Abhaykoul's picture
Adding Evaluation Results (#1)
0cf1fd5 verified
metadata
language:
  - en
license: other
datasets:
  - OEvortex/vortex-mini
  - yahma/alpaca-cleaned
license_name: tongyi-qianwen-research
license_link: https://huggingface.co/Qwen/Qwen1.5-0.5B/blob/main/LICENSE
pipeline_tag: text-generation
model-index:
  - name: Qwen1.5-0.5B-vortex-v2
    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: 30.63
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Abhaykoul/Qwen1.5-0.5B-vortex-v2
          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: 45.54
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Abhaykoul/Qwen1.5-0.5B-vortex-v2
          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: 36.29
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Abhaykoul/Qwen1.5-0.5B-vortex-v2
          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: 44.29
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Abhaykoul/Qwen1.5-0.5B-vortex-v2
          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: 56.04
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Abhaykoul/Qwen1.5-0.5B-vortex-v2
          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: 5.91
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Abhaykoul/Qwen1.5-0.5B-vortex-v2
          name: Open LLM Leaderboard

Qwen1.5-0.5B-vortex-v2 model card

Qwen1.5-0.5B-vortex-v2 is a dealigned chat finetune of the original fantastic Qwen1.5-0.5B model by the Qwen team.

This model was trained on the Vortex mini dataset and alpaca-cleaned using axolotl for 4 epoch

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 36.45
AI2 Reasoning Challenge (25-Shot) 30.63
HellaSwag (10-Shot) 45.54
MMLU (5-Shot) 36.29
TruthfulQA (0-shot) 44.29
Winogrande (5-shot) 56.04
GSM8k (5-shot) 5.91