Gemma 7B Zephyr DPO
The Zephyr DPO recipe applied on top of SFT finetuned 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: wandb/gemma-7b-zephyr-sft
Recipe
We trained using the DPO script in 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. | 61.62 |
| AI2 Reasoning Challenge (25-Shot) | 60.84 |
| HellaSwag (10-Shot) | 80.44 |
| MMLU (5-Shot) | 60.60 |
| TruthfulQA (0-shot) | 42.48 |
| Winogrande (5-shot) | 75.37 |
| GSM8k (5-shot) | 49.96 |
- Downloads last month
- 14
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for wandb/gemma-7b-zephyr-dpo
Dataset used to train wandb/gemma-7b-zephyr-dpo
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard60.840
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard80.440
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard60.600
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard42.480
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard75.370
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard49.960