README.md

metadata

license: other
tags:
  - merge
license_name: yi-license
license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
model-index:
  - name: Kyllene-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: 64.85
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/Kyllene-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: 84.51
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/Kyllene-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: 73.33
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/Kyllene-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: 57.89
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/Kyllene-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: 78.22
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/Kyllene-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: 30.4
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/Kyllene-v1.0
          name: Open LLM Leaderboard

Kyllene 57B v1.0

Model Details

• A result of using SLERP merge of TeeZee/2xbagel-dpo-34b-v0.2 and TeeZee/2xNous-Capybara-34B.
• The resulting model has 100 layers and approximately 57 billion parameters.
• 200K context length
• See mergekit-config.yml for details on the merge method used.

Warning: This model can produce NSFW content!

Results

• produces SFW nad NSFW content without issues, switches context seamlessly.
• good at following instructions
• pretty close to my ideal RPG/ERP everyday model (but more tests are needed)

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.	64.86
AI2 Reasoning Challenge (25-Shot)	64.85
HellaSwag (10-Shot)	84.51
MMLU (5-Shot)	73.33
TruthfulQA (0-shot)	57.89
Winogrande (5-shot)	78.22
GSM8k (5-shot)	30.40