NeuralNovel/Gecko-7B-v0.1-DPO
Designed to generate instructive and narrative text, with a focus on mathematics & numeracy.
Full-parameter fine-tune (FFT) of Mistral-7B-Instruct-v0.2, with apache-2.0 license.
You may download and use this model for research, training and commercial purposes.
This model is suitable for commercial deployment.
Data-set
The model was finetuned using the orca_dpo_pairs dataset
Summary
Fine-tuned with the intention of following all prompt directions, making it more suitable for math questions and problem solving.
Out-of-Scope Use
The model may not perform well in scenarios unrelated to instructive and narrative text generation. Misuse or applications outside its designed scope may result in suboptimal outcomes.
Bias, Risks, and Limitations
This model may not work as intended. As such all users are encouraged to use this model with caution and respect.
This model is for testing and research purposes only, it has reduced levels of alignment and as a result may produce NSFW or harmful content. The user is responsible for their output and must use this model responsibly.
Hardware and Training
Trained on a single 80GB A100 for 2 hours trained using Axolotl
Thank you to h2m for the generous funding.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 63.22 |
| AI2 Reasoning Challenge (25-Shot) | 56.74 |
| HellaSwag (10-Shot) | 82.38 |
| MMLU (5-Shot) | 60.42 |
| TruthfulQA (0-shot) | 57.42 |
| Winogrande (5-shot) | 77.35 |
| GSM8k (5-shot) | 45.03 |