Downloads · 30 days
67
16% of all-time downloads
unsloth_finetune
see-k/unsloth_finetune
unsloth_finetune is a feature extraction model from see-k. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as apache-2.0.
- Developed by: see-k - License: apache-2.0 - Finetuned from model : deepseek-ai/DeepSeek-OCR
All-time downloads
424
Public
Parameters
3.3B
26.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf6.7 GB · 50%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- License
- apache-2.0
- Model type
- DeepseekOCR
- Access
- Public
- Created
- Jun 17, 2026
- Updated
- Jun 18, 2026
- SHA
- 3600fdbc
Base models
Model card
From the Hugging Face model README
Uploaded finetuned model
- Developed by: see-k
- License: apache-2.0
- Finetuned from model : deepseek-ai/DeepSeek-OCR
This deepseek_vl_v2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Task
- Feature Extraction
- Library
- transformers
- Type
- DeepseekOCR
- License
- apache-2.0
- Languages
- en
- Created
- Jun 17, 2026
- Updated
- Jun 18, 2026