README.md

metadata

language:
  - en
  - zh
license: other
base_model: internlm/internlm2-base-20b
model-index:
  - name: internlm2-base-20b-llama
    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: 62.97
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=intervitens/internlm2-base-20b-llama
          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: 82.15
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=intervitens/internlm2-base-20b-llama
          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: 63.78
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=intervitens/internlm2-base-20b-llama
          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: 44.11
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=intervitens/internlm2-base-20b-llama
          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=intervitens/internlm2-base-20b-llama
          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: 44.88
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=intervitens/internlm2-base-20b-llama
          name: Open LLM Leaderboard

Special thanks to Charles Goddard for the conversion script to create llama models from internlm

internlm2-base-20b converted into Llama-format weights. As with 7B, not 100% sure if it's a correct conversion yet - play with at your own risk.

Subject to internlm's license.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	62.69
AI2 Reasoning Challenge (25-Shot)	62.97
HellaSwag (10-Shot)	82.15
MMLU (5-Shot)	63.78
TruthfulQA (0-shot)	44.11
Winogrande (5-shot)	78.22
GSM8k (5-shot)	44.88