README.md

metadata

license: apache-2.0
model-index:
  - name: LeoScorpius-7B-Chat-DPO
    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: 70.48
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=viethq188/LeoScorpius-7B-Chat-DPO
          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: 87.97
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=viethq188/LeoScorpius-7B-Chat-DPO
          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: 65.08
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=viethq188/LeoScorpius-7B-Chat-DPO
          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: 68.83
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=viethq188/LeoScorpius-7B-Chat-DPO
          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: 82.08
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=viethq188/LeoScorpius-7B-Chat-DPO
          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: 69.07
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=viethq188/LeoScorpius-7B-Chat-DPO
          name: Open LLM Leaderboard

Updated: 14th December 2023

We are ranked 3th on the overall leaderboard and 1st in the 7B Hugging Face Leaderboard!! 🔥🔥🔥

Finetune DPO viethq188/LeoScorpius-7B with Nectar dataset

You can use alpaca template.

template_format = """{system}
### Instruction:
{prompt}

### Response:
"""

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	73.92
AI2 Reasoning Challenge (25-Shot)	70.48
HellaSwag (10-Shot)	87.97
MMLU (5-Shot)	65.08
TruthfulQA (0-shot)	68.83
Winogrande (5-shot)	82.08
GSM8k (5-shot)	69.07