README.md

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

Technical notes

• 108 layers,DUS procedure, mistral(32)->SOLAR(48)->GALAXY(72)->NEBULA(108)
• 23.8B parameters
• model created as an 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
• comparable memory footprint to 20B and 23B models based on llama
• 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:

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