Hugging Face's logo

tanganke
/
clip-vit-base-patch32_kmnist

TensorBoard
Safetensors
clip_vision_model
Model card Files Metrics Community

Model Card

Training Details

Adam Optimizer with a constant learning rate 1e-5 for 4000 steps training (batch_size=128). Only the vision encoder is fine-tuned.

Evaluation Results

Test set accuracy:

  • pre-trained: 0.09950000047683716
  • fine-tuned: 0.9822999835014343
Downloads last month
301
Safetensors
Model size
87.5M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.

Model tree for tanganke/clip-vit-base-patch32_kmnist

Base model

openai/clip-vit-base-patch32
Finetuned
(56)
this model

Dataset used to train tanganke/clip-vit-base-patch32_kmnist