TeeZee's picture
Upload README.md
5958650 verified
metadata
language:
  - en
license: apache-2.0
tags:
  - not-for-all-audiences
datasets:
  - Intel/orca_dpo_pairs
  - athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW
  - Open-Orca/SlimOrca
  - MinervaAI/Aesir-Preview
  - allenai/ultrafeedback_binarized_cleaned
model-index:
  - name: NEBULA-23B-v1.0
    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: 66.72
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/NEBULA-23B-v1.0
          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: 86.98
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/NEBULA-23B-v1.0
          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: 65.4
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/NEBULA-23B-v1.0
          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: 57.6
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/NEBULA-23B-v1.0
          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: 82.95
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/NEBULA-23B-v1.0
          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: 0
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/NEBULA-23B-v1.0
          name: Open LLM Leaderboard

NEBULA-23.8B-v1.0

image/png

Technical notes

  • 108 layers,DUS procedure, mistral(32)->SOLAR(48)->GALAXY(72)->NEBULA(108)
  • 23.8B parameters
  • model created as a extension of depth upscaling procedure used for SOLAR by upstage

Results

  • model can and will produce NSFW content
  • GSM8k evaluation seems to be often broken, HellaSwag, Winograde and TQA show that its a smart model
  • RP and ERP work surprisingly good and I didn't encounter any GPTisms yet
  • lower memory footprint than 20B and 23B models
  • follows character card very well
  • NSFW output feels fresh comparing to existing models

Finetuning for RP

  • SFT using MinervaAI/Aesir-Preview dataset, 10 epochs
  • DPO using athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW dataset, 1 epoch
  • SFT using 1xAda6000, 10h
  • DPO using 1x3090, 30h
  • jupyter notebooks or mergekit configs for anyone wanting to reproduce/reuse scripts - just drop me a message

Prompt template

  • Alpaca
  • chat template is embedded in tokenizer config, should load automatically

Context size

  • 4096

All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel: Buy Me A Coffee

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 59.94
AI2 Reasoning Challenge (25-Shot) 66.72
HellaSwag (10-Shot) 86.98
MMLU (5-Shot) 65.40
TruthfulQA (0-shot) 57.60
Winogrande (5-shot) 82.95
GSM8k (5-shot) 0.00