README.md

metadata

license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - FelixChao/WestSeverus-7B-DPO-v2
  - bardsai/jaskier-7b-dpo-v5.6
  - AbacusResearch/haLLAwa3
  - cognitivecomputations/WestLake-7B-v2-laser
model-index:
  - name: jaLLAbi2-7b
    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: 71.67
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AbacusResearch/jaLLAbi2-7b
          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: 88.29
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AbacusResearch/jaLLAbi2-7b
          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: 64.92
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AbacusResearch/jaLLAbi2-7b
          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: 70.16
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AbacusResearch/jaLLAbi2-7b
          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: 83.35
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AbacusResearch/jaLLAbi2-7b
          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: 71.95
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AbacusResearch/jaLLAbi2-7b
          name: Open LLM Leaderboard

jaLLAbi2-7b

jaLLAbi2-7b is a merge of the following models using mergekit:

• FelixChao/WestSeverus-7B-DPO-v2
• bardsai/jaskier-7b-dpo-v5.6
• AbacusResearch/haLLAwa3
• cognitivecomputations/WestLake-7B-v2-laser

🧩 Configuration

```yaml models:

• model: eren23/ogno-monarch-jaskier-merge-7b

  No parameters necessary for base model

• model: FelixChao/WestSeverus-7B-DPO-v2 #Emphasize the beginning of Vicuna format models parameters: weight: 0.2 density: 0.59
• model: bardsai/jaskier-7b-dpo-v5.6 parameters: weight: 0.2 density: 0.55

Vicuna format

• model: AbacusResearch/haLLAwa3 parameters: weight: 0.3 density: 0.55
• model: cognitivecomputations/WestLake-7B-v2-laser parameters: weight: 0.3 density: 0.55

merge_method: dare_ties base_model: eren23/ogno-monarch-jaskier-merge-7b parameters: int8_mask: true dtype: bfloat16 random_seed: 0 ```

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	75.06
AI2 Reasoning Challenge (25-Shot)	71.67
HellaSwag (10-Shot)	88.29
MMLU (5-Shot)	64.92
TruthfulQA (0-shot)	70.16
Winogrande (5-shot)	83.35
GSM8k (5-shot)	71.95