SlimMelodicMaid / README.md
Azazelle's picture
Adding Evaluation Results (#1)
e40c91c verified
metadata
license: cc-by-4.0
tags:
  - mistral
  - merge
pipeline_tag: text-generation
model-index:
  - name: SlimMelodicMaid
    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: 67.15
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/SlimMelodicMaid
          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: 86.01
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/SlimMelodicMaid
          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: 64.75
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/SlimMelodicMaid
          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: 60.88
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/SlimMelodicMaid
          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: 78.61
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/SlimMelodicMaid
          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: 60.8
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/SlimMelodicMaid
          name: Open LLM Leaderboard

Model Card for xDAN-SlimOrca

Slerp merge of Silicon-Maid-7B, piano-medley-7b, xDAN-L1-Chat-RL-v1, and mistral-7b-slimorcaboros.

.yaml file for mergekit

slices:
  - sources:
      - model: Azazelle/Silicon-Medley
        layer_range: [0, 32]
      - model: Azazelle/xDAN-SlimOrca
        layer_range: [0, 32]
merge_method: slerp
base_model: mistralai/Mistral-7B-v0.1
parameters:
  t:
    - filter: self_attn
      value: [0.19, 0.59, 0.43, 0.76, 1]
    - filter: mlp
      value: [0.81, 0.41, 0.57, 0.24, 0]
    - value: 0.5 # fallback for rest of tensors
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 69.70
AI2 Reasoning Challenge (25-Shot) 67.15
HellaSwag (10-Shot) 86.01
MMLU (5-Shot) 64.75
TruthfulQA (0-shot) 60.88
Winogrande (5-shot) 78.61
GSM8k (5-shot) 60.80