Downloads · 30 days
22
14% of all-time downloads
LightOnOCR-1B-1025-ft-ja3-full
aipib/LightOnOCR-1B-1025-ft-ja3-full
LightOnOCR-1B-1025-ft-ja3-full is a machine learning model from aipib. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This model is a fine-tuned version of lightonai/LightOnOCR-1B-1025 on aipib/japanese-text-image-retrieval-small2.
All-time downloads
162
Public
Parameters
1B
8.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2 GB · 99%
At a glance
- License
- apache-2.0
- Model type
- mistral3
- Access
- Public
- Created
- Dec 24, 2025
- Updated
- Jan 4, 2026
- SHA
- 2885c2a0
Base models
Model card
From the Hugging Face model README
This model is a fine-tuned version of lightonai/LightOnOCR-1B-1025 on aipib/japanese-text-image-retrieval-small2.
It achieves the following results on the evaluation set:
-VAL_Loss: 1.07
Intended uses & limitations Please refer the original information
Training hyperparameters The following hyperparameters were used during training:
learning_rate: 1e-04 train_batch_size: 4 eval_batch_size: 4 seed: 42 gradient_accumulation_steps: 4 total_train_batch_size: 16 optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments lr_scheduler_type: linear lr_scheduler_warmup_steps: 10 training_steps: 100
Framework versions PEFT 0.18.0 Transformers 5.0.0.dev0 Pytorch 2.9.1 Datasets 4.4.1 Tokenizers 0.22.1
- Type
- mistral3
- License
- apache-2.0
- Created
- Dec 24, 2025
- Updated
- Jan 4, 2026