README.md

metadata

license: other
library_name: transformers
datasets:
  - HuggingFaceH4/ultrachat_200k
base_model: google/gemma-2b
license_name: gemma-terms-of-use
license_link: https://ai.google.dev/gemma/terms
model-index:
  - name: gemma-2b-zephyr-sft
    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: 49.74
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-2b-zephyr-sft
          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: 72.38
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-2b-zephyr-sft
          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: 41.37
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-2b-zephyr-sft
          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: 34.42
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-2b-zephyr-sft
          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: 66.93
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-2b-zephyr-sft
          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: 18.27
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-2b-zephyr-sft
          name: Open LLM Leaderboard

Gemma 2B Zephyr SFT

The Zephyr SFT recipe applied on top of Gemma 2B

Model description

• Model type: A 2.5B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
• Language(s) (NLP): Primarily English
• Finetuned from model: google/gemma-7b

Recipe

We trained using the alignment handbook recipe and logging to W&B

Visit the W&B workspace here

License

This model has the same license as the original Gemma model collection

Compute provided by Lambda Labs - 8xA100 80GB node

• Around 2 hours to train

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	47.18
AI2 Reasoning Challenge (25-Shot)	49.74
HellaSwag (10-Shot)	72.38
MMLU (5-Shot)	41.37
TruthfulQA (0-shot)	34.42
Winogrande (5-shot)	66.93
GSM8k (5-shot)	18.27