README.md

metadata

language:
  - en
license: cc-by-sa-4.0
library_name: transformers
tags:
  - finetune
base_model:
  - jeiku/FloraBase
  - jeiku/Synthetic_Soul_1k_Mistral_128
datasets:
  - ResplendentAI/Synthetic_Soul_1k
model-index:
  - name: Flora_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: 72.1
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_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: 88.31
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_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: 64.16
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_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: 71.19
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_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: 84.45
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_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: 65.35
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Flora_7B
          name: Open LLM Leaderboard

Flora

Quants available here:

https://huggingface.co/bartowski/Flora_7B-GGUF

https://huggingface.co/bartowski/Flora_7B-exl2

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

Configuration

The following YAML configuration was used to produce this model:

merge_method: linear
models:
  - model: jeiku/FloraBase+jeiku/Synthetic_Soul_1k_Mistral_128
    parameters:
      weight: 1       
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.26
AI2 Reasoning Challenge (25-Shot)	72.10
HellaSwag (10-Shot)	88.31
MMLU (5-Shot)	64.16
TruthfulQA (0-shot)	71.19
Winogrande (5-shot)	84.45
GSM8k (5-shot)	65.35