README.md

metadata

license: other
pipeline_tag: text-generation
model-index:
  - name: internlm2-chat-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: 63.65
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bartowski/internlm2-chat-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: 82.58
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bartowski/internlm2-chat-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: 66.89
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bartowski/internlm2-chat-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: 48.74
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bartowski/internlm2-chat-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: 79.56
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bartowski/internlm2-chat-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: 33.97
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bartowski/internlm2-chat-20b-llama
          name: Open LLM Leaderboard

InternLM

 

InternLM ^HOT

 

💻Github Repo

Converted using Charles Goddard's conversion script to create llama models from internlm

Original REPO link: https://huggingface.co/internlm/internlm2-chat-20b

ExLlamaV2 quants: https://huggingface.co/bartowski/internlm2-chat-20b-llama-exl2

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	62.56
AI2 Reasoning Challenge (25-Shot)	63.65
HellaSwag (10-Shot)	82.58
MMLU (5-Shot)	66.89
TruthfulQA (0-shot)	48.74
Winogrande (5-shot)	79.56
GSM8k (5-shot)	33.97