Downloads · 30 days
8
1% of all-time downloads
qikp/kite-6.1-18m-r1
kite-6.1-18m-r1 is a text generation model from qikp. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as cc0-1.0.
🎉 You are looking at Kite 6.1 Release 1, which is our 3rd attempt at combatting underfitting!
Downloads · 30 days
8
1% of all-time downloads
All-time downloads
819
Public
Parameters
18.1M
72.4 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors72.4 MB · 99%
From the Hugging Face model README
🎉 You are looking at Kite 6.1 Release 1, which is our 3rd attempt at combatting underfitting!
Kite is a small, trained, 18 million parameter language model.
It was trained on a tokenized version of qikp/small-data-3.2, which is a mixture of various datasets, using 2 epochs, 32 batch size, 1e-3 learning rate, and the pika 4 tokenizer.
Also, evaluation on a tokenized and truncated byunggill/gpt-2-output was done during training.
Due to its size, the model is not suitable for production workloads.