metadata

language:
  - en
license: apache-2.0
library_name: transformers
tags:
  - roleplay
  - text-generation-inference
model-index:
  - name: EstopianMaid-13B
    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: 60.49
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KatyTheCutie/EstopianMaid-13B
          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: 83.49
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KatyTheCutie/EstopianMaid-13B
          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: 56.18
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KatyTheCutie/EstopianMaid-13B
          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: 52.35
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KatyTheCutie/EstopianMaid-13B
          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: 75.53
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KatyTheCutie/EstopianMaid-13B
          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: 9.17
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KatyTheCutie/EstopianMaid-13B
          name: Open LLM Leaderboard

Based on feedback Estopian made can:

EstopianMaid is good at sticking to the character card.
maintains coherency in a setting with multiple characters.
Able to create new scenario's
Feature from Thespis:

Prompt Template: Alpaca

Instruction:

{prompt}

Response:

Recommended settings:

SillyTavern Default Preset.
Temperature: 0.7
Min-P: 0.3
Amount to Gen: 256
Top P: 1
Repetition penalty: 1.10

Models used:

BlueNipples/TimeCrystal-l2-13B
cgato/Thespis-13b-DPO-v0.7
KoboldAI/LLaMA2-13B-Estopia
NeverSleep/Noromaid-13B-0.4-DPO
Doctor-Shotgun/cat-v1.0-13b

Feedback is always appreciated! Thank you KoboldAI for their usage of their MergeBox and Caitlyn G. for their support and feedback.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	56.20
AI2 Reasoning Challenge (25-Shot)	60.49
HellaSwag (10-Shot)	83.49
MMLU (5-Shot)	56.18
TruthfulQA (0-shot)	52.35
Winogrande (5-shot)	75.53
GSM8k (5-shot)	9.17

Instruction:

Response:

Open LLM Leaderboard Evaluation Results