README.md

metadata

language:
  - en
license: cc-by-sa-4.0
library_name: transformers
datasets:
  - mlabonne/chatml_dpo_pairs
  - ResplendentAI/Synthetic_Soul_1k
model-index:
  - name: Flora_DPO_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: 71.76
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_DPO_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: 88.28
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_DPO_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: 64.13
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_DPO_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: 71.08
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_DPO_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: 84.53
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_DPO_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: 65.81
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_DPO_7B
          name: Open LLM Leaderboard

Flora DPO

Finetuned with this DPO dataset: https://huggingface.co/datasets/mlabonne/chatml_dpo_pairs

Quants available here:

https://huggingface.co/solidrust/Flora-7B-DPO-AWQ

https://huggingface.co/Test157t/ResplendentAI-Flora_DPO_7B-5bpw-exl2

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.26
AI2 Reasoning Challenge (25-Shot)	71.76
HellaSwag (10-Shot)	88.28
MMLU (5-Shot)	64.13
TruthfulQA (0-shot)	71.08
Winogrande (5-shot)	84.53
GSM8k (5-shot)	65.81