README.md

metadata

license: cc-by-nc-nd-4.0
model-index:
  - name: caigun-lora-model-34B-v2
    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: 65.02
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=APMIC/caigun-lora-model-34B-v2
          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: 85.28
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=APMIC/caigun-lora-model-34B-v2
          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: 75.69
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=APMIC/caigun-lora-model-34B-v2
          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: 58.03
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=APMIC/caigun-lora-model-34B-v2
          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: 83.03
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=APMIC/caigun-lora-model-34B-v2
          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: 60.12
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=APMIC/caigun-lora-model-34B-v2
          name: Open LLM Leaderboard

This is model finetuned on Orca style dataset.

Model Details:

Model Name: caigun-lora-model-33B

Model Version: 1.0

Date Created: 2023/12/21

Model Overview:

Intended Use: caigun-lora-model-33B is a LLM designed for various purpose.

Training Data: Orca style dataset

Model Architecture: It is based on LLaMA architecture.

Training Procedure: [Stay tuned for updates]

Model Performance: [Stay tuned for updates]

Potential Risks: It's important to consider ethical implications related to the use of our model.

Updates and Version History:
Version 1.0: finetuned on fake news detection.
Version 2.0: finetuned on Orca style dataset.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	71.19
AI2 Reasoning Challenge (25-Shot)	65.02
HellaSwag (10-Shot)	85.28
MMLU (5-Shot)	75.69
TruthfulQA (0-shot)	58.03
Winogrande (5-shot)	83.03
GSM8k (5-shot)	60.12