---
base_model:
- facebook/convnext-base-224
library_name: transformers
tags:
- fusion-bench
- merge
---
# Deep Model Fusion

Fine-tuned ResNet model on dataset mnist.

## Models Merged

This is a merged model created using [fusion-bench](https://github.com/tanganke/fusion_bench).

The following models were included in the merge:


- base model: facebook/convnext-base-224


## Configuration

The following YAML configuration was used to produce this model:

### Algorithm Configuration

```yaml
_recursive_: false
_target_: fusion_bench.method.classification.image_classification_finetune.ImageClassificationFineTuning
_usage_: null
_version_: 0.2.31.dev0
dataloader_kwargs:
  batch_size: 64
  num_workers: 8
  pin_memory: true
label_smoothing: 0
lr_scheduler: null
max_epochs: -1
max_steps: 4000
optimizer:
  _target_: torch.optim.SGD
  lr: 0.01
  momentum: 0.9
  weight_decay: 0.0001
save_interval: 1000
save_on_train_epoch_end: false
save_top_k: -1
training_data_ratio: null
```

### Model Pool Configuration

```yaml
_recursive_: false
_target_: fusion_bench.modelpool.convnext_for_image_classification.ConvNextForImageClassificationPool
_usage_: null
_version_: 0.2.31.dev0
models:
  _pretrained_:
    config_path: facebook/convnext-base-224
    dataset_name: mnist
    pretrained: true
test_datasets: null
train_datasets:
  mnist:
    _target_: datasets.load_dataset
    path: mnist
    split: train
val_datasets:
  mnist:
    _target_: datasets.load_dataset
    path: mnist
    split: test
```