README.md

metadata

license: other
license_name: qwen
license_link: LICENSE
model-index:
  - name: Qwen-72B-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: 64.85
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Qwen-72B-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: 83.27
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Qwen-72B-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: 73.66
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Qwen-72B-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: 57.6
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Qwen-72B-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: 81.53
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Qwen-72B-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: 56.25
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Qwen-72B-Llama
          name: Open LLM Leaderboard

🦙 Qwen-72B-Llama

This is the 🦙 llamafied version of Qwen/Qwen-72B.

🛠️ Reproduction

I used this script to convert the weights:

LLaMA-Factory/tests/llamafy_qwen.py

🔠 Tokenizer

After I converted the weights, I took the tokenizer from KnutJaegersberg/Qwen-14B-Llamafied and uploaded it to this repository.

📊 Eval Scores Compared to Original Model

Here are some of the evaluation score comparisons based on the Open LLM Leaderboard.

Metric	Qwen-72B	Qwen-72B-Llama
Avg.	73.6	69.53
ARC (25-shot)	65.19	64.85
HellaSwag (10-shot)	85.94	83.27
MMLU (5-shot)	77.37	73.66
TruthfulQA (0-shot)	60.19	57.6
Winogrande (5-shot)	82.48	81.53
GSM8K (5-shot)	70.43	56.25

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	69.53
AI2 Reasoning Challenge (25-Shot)	64.85
HellaSwag (10-Shot)	83.27
MMLU (5-Shot)	73.66
TruthfulQA (0-shot)	57.60
Winogrande (5-shot)	81.53
GSM8k (5-shot)	56.25