license, library_name, datasets, base_model, license_name, license_link, model-index

license	library_name	datasets	base_model	license_name	license_link	model-index
other	transformers	HuggingFaceH4/ultrachat_200k	google/gemma-7b	gemma-terms-of-use	https://ai.google.dev/gemma/terms	name results gemma-7b-zephyr-sft task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 61.43 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-7b-zephyr-sft Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 80.73 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-7b-zephyr-sft Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 60.33 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-7b-zephyr-sft Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 43.35 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-7b-zephyr-sft Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 74.19 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-7b-zephyr-sft Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 49.81 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-7b-zephyr-sft Open LLM Leaderboard

Gemma 7B Zephyr SFT

The Zephyr SFT recipe applied on top of Gemma 7B

Model description

• Model type: A 8.5B 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

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	61.64
AI2 Reasoning Challenge (25-Shot)	61.43
HellaSwag (10-Shot)	80.73
MMLU (5-Shot)	60.33
TruthfulQA (0-shot)	43.35
Winogrande (5-shot)	74.19
GSM8k (5-shot)	49.81