Downloads · 30 days
14
16% of all-time downloads
kite-6.5-15m
qikp/kite-6.5-15m
kite-6.5-15m 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 6.5, which uses Ultra-FineWeb!
All-time downloads
88
Public
Parameters
15M
59.8 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors59.8 MB · 99%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- cc0-1.0
- Model type
- qwen2
- Access
- Public
- Created
- Jul 22, 2026
- Updated
- Jul 22, 2026
- SHA
- 04222ed8
Try a prompt
Datasets
Model card
From the Hugging Face model README
Kite
🎉 You are looking at Kite 6.5, which uses Ultra-FineWeb!
Kite is a small, trained, 15 million parameter language model.
Training
It was trained on 100K rows (<3072 length) of Ultra-FineWeb, using 1 epoch, 32 batch size, 1e-3 learning rate, and the pika 5 tokenizer.
Limitations
Due to its size, the model is not suitable for production workloads. Additionally, most of the training corpus is really short documents.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen2
- License
- cc0-1.0
- Languages
- en
- Created
- Jul 22, 2026
- Updated
- Jul 22, 2026