README.md

metadata

license: other
tags:
  - merge
  - not-for-all-audiences
license_name: microsoft-research-license
model-index:
  - name: DarkForest-20B-v2.0
    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: 63.74
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
          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: 86.32
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
          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: 59.79
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
          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: 56.14
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
          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: 77.9
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
          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: 23.28
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
          name: Open LLM Leaderboard

DarkForest 20B v2.0

Model Details

• To create this model two step procedure was used. First a new 20B model was created using microsoft/Orca-2-13b and KoboldAI/LLaMA2-13B-Erebus-v3 , deatils of the merge in darkforest_v2_step1.yml
• then jebcarter/psyonic-cetacean-20B
• and TeeZee/BigMaid-20B-v1.0 was used to produce the final model, merge config in darkforest_v2_step2.yml
• The resulting model has approximately 20 billion parameters.

Warning: This model can produce NSFW content!

Results

• main difference to v1.0 - model has much better sense of humor.
• produces SFW nad NSFW content without issues, switches context seamlessly.
• good at following instructions.
• good at tracking multiple characters in one scene.
• very creative, scenarios produced are mature and complicated, model doesn't shy from writing about PTSD, mental issues or complicated relationships.
• NSFW output is more creative and suprising than typical limaRP output.
• definitely for mature audiences, not only because of vivid NSFW content but also because of overall maturity of stories it produces.
• This is NOT Harry Potter level storytelling.

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.	61.19
AI2 Reasoning Challenge (25-Shot)	63.74
HellaSwag (10-Shot)	86.32
MMLU (5-Shot)	59.79
TruthfulQA (0-shot)	56.14
Winogrande (5-shot)	77.90
GSM8k (5-shot)	23.28