README.md

metadata

license: llama3.1
datasets:
  - agentlans/crash-course
base_model:
  - agentlans/Llama3.1-SuperDeepFuse
model-index:
  - name: Llama3.1-SuperDeepFuse-CrashCourse12K
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: wis-k/instruction-following-eval
          split: train
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 71.87
            name: averaged accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FLlama3.1-SuperDeepFuse-CrashCourse12K
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: SaylorTwift/bbh
          split: test
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 31.83
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FLlama3.1-SuperDeepFuse-CrashCourse12K
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: lighteval/MATH-Hard
          split: test
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 17.67
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FLlama3.1-SuperDeepFuse-CrashCourse12K
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          split: train
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 8.39
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FLlama3.1-SuperDeepFuse-CrashCourse12K
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 8.6
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FLlama3.1-SuperDeepFuse-CrashCourse12K
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 29.24
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FLlama3.1-SuperDeepFuse-CrashCourse12K
          name: Open LLM Leaderboard

Llama3.1-SuperDeepFuse-CrashCourse12K

Llama3.1-SuperDeepFuse-CrashCourse12K is an 8B parameter language model based on Llama3.1-SuperDeepFuse and further fine-tuned on agentlans/crash-course.

Model Details

• Base Model: Llama3.1-SuperDeepFuse (8B parameters)
• Fine-tuning Dataset: 12 000 samples from agentlans/crash-course (containing samples from 10 high-quality instruct datasets)
• Model Type: Instruction-tuned language model
• Language(s): Multilingual
• License: Follows standard Llama 3.1 usage terms

Training Procedure

Fine-tuning

• Method: LoRA (Low-Rank Adaptation)
• Optimizer: AdamW
• Learning Rate: 5e-5
• Batch Size: 2 per device
• Gradient Accumulation Steps: 8
• Training Epochs: 1
• Max Sequence Length: 2048
• LoRA Configuration:
  • Rank: 8
  • Alpha: 16
  • Dropout: 0.5
  • Target: all layers
• Quantization: 4-bit (bitsandbytes)
• Precision: BF16
• Other Techniques: NEFTune (noise alpha: 5), RS-LoRA

Performance and Limitations

This model potentially offers:

• Enhanced multi-task reasoning
• Improved performance in mathematics and coding tasks
• Better instruction-following abilities

However:

• Performance may be limited compared to larger model variants
• Can produce misleading or incorrect outputs
• Outputs should be independently verified for critical applications

Additional Information

• For the original model, see agentlans/Llama3.1-SuperDeepFuse
• For the base Llama 3.1 model, including training data and model architecture, refer to the original Llama 3.1 model card.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here! Summarized results can be found here!

Metric	Value (%)
Average	27.93
IFEval (0-Shot)	71.87
BBH (3-Shot)	31.83
MATH Lvl 5 (4-Shot)	17.67
GPQA (0-shot)	8.39
MuSR (0-shot)	8.60
MMLU-PRO (5-shot)	29.24