Hugging Face's logo

luke-kr
/
colqwen_h

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
colqwen_h / README.md
luke-kr's picture
luke-kr
luke-kr/colpali-ft
b7a2eb8 verified
preview code
|
raw
history blame contribute delete
1.29 kB
metadata
library_name: peft
license: gemma
base_model: vidore/colpali-v1.2-hf
tags:
  - generated_from_trainer
model-index:
  - name: colqwen_h
    results: []

colqwen_h

This model is a fine-tuned version of vidore/colpali-v1.2-hf on an unknown dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Use adamw_torch 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: 100
  • num_epochs: 12

Training results

Framework versions

  • PEFT 0.14.0
  • Transformers 4.49.0
  • Pytorch 2.5.0a0+e000cf0ad9.nv24.10
  • Datasets 3.3.2
  • Tokenizers 0.21.0