Downloads · 30 days
0
nanoalpaca-3b
Sovenok-Hacker/nanoalpaca-3b
nanoalpaca-3b is a question answering model from Sovenok-Hacker. Use it when the input is a question plus a passage. The card lists the license as gpl-3.0.
Minimal Alpaca-LORA trained with databricks/databricks-dolly-v2-15k dataset and based on OpenLLaMA-3B-600BT.
Access
Public
Updated May 30, 2023
Repo size
1.9 GB
Likes
6
Public
Repo makeup
Click a slice to open those files.
.bin1.9 GB · 99%
At a glance
- Task
- Question Answering
- License
- gpl-3.0
- Access
- Public
- Created
- May 29, 2023
- Updated
- May 30, 2023
- SHA
- 2394a816
Try a prompt
Datasets
Model card
From the Hugging Face model README
Minimal Alpaca-LORA trained with databricks/databricks-dolly-v2-15k dataset and based on OpenLLaMA-3B-600BT.
There is a pre-trained LoRA adapter and a Colab Jupyter notebook for fine-tuning (about 3 hours for 1 epoch on T4).
- Task
- Question Answering
- License
- gpl-3.0
- Languages
- en
- Created
- May 29, 2023
- Updated
- May 30, 2023