README.md

metadata

language:
  - en
license: llama2
tags:
  - dare
  - super mario merge
  - pytorch
  - llama
  - llama-2
  - merge
pipeline_tag: text-generation
inference: false
model-index:
  - name: llama-megamerge-dare-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: 60.58
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/llama-megamerge-dare-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
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/llama-megamerge-dare-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: 54.91
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/llama-megamerge-dare-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: 45.76
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/llama-megamerge-dare-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: 76.16
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/llama-megamerge-dare-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: 28.51
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/llama-megamerge-dare-13b
          name: Open LLM Leaderboard

llama 13b mega merge

The following were merged with hyperparams p=0.1 and lambda=2.

The first entry is the base model.

meta-llama/Llama-2-13b-hf
ajibawa-2023/Code-13B
migtissera/Synthia-13B
meta-math/MetaMath-13B-V1.0
FPHam/Sydney_Overthinker_13b_HF
allenai/tulu-2-dpo-13b
ajibawa-2023/Python-Code-13B
Doctor-Shotgun/cat-v1.0-13b
NeverSleep/Noromaid-13b-v0.1.1

Using https://github.com/martyn/safetensors-merge-supermario

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	58.15
AI2 Reasoning Challenge (25-Shot)	60.58
HellaSwag (10-Shot)	83.00
MMLU (5-Shot)	54.91
TruthfulQA (0-shot)	45.76
Winogrande (5-shot)	76.16
GSM8k (5-shot)	28.51