Upload folder using huggingface_hub

README.md

@@ -0,0 +1,77 @@
+---
+base_model:
+- facebook/convnext-base-224
+library_name: transformers
+tags:
+- fusion-bench
+- merge
+---
+# Deep Model Fusion
+
+Fine-tuned ResNet model on dataset dtd.
+
+## 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: dtd
+    pretrained: true
+test_datasets: null
+train_datasets:
+  dtd:
+    _target_: datasets.load_dataset
+    path: tanganke/dtd
+    split: train
+val_datasets:
+  dtd:
+    _target_: datasets.load_dataset
+    path: tanganke/dtd
+    split: test
+```
+

cli.log

@@ -0,0 +1,26 @@
+[2026-01-08 04:49:05,782][fusion_bench.programs.fusion_program][INFO] - Running the model fusion program.
+[2026-01-08 04:49:05,785][fusion_bench.programs.fusion_program][INFO] - loading model pool
+[2026-01-08 04:49:08,035][fusion_bench.programs.fusion_program][INFO] - loading method
+[2026-01-08 04:49:08,098][fusion_bench.method.classification.image_classification_finetune][INFO] - Training interval: step
+[2026-01-08 04:49:08,098][fusion_bench.method.classification.image_classification_finetune][INFO] - Max epochs: -1, max steps: 4000
+[2026-01-08 04:49:08,099][fusion_bench.programs.fusion_program][INFO] - loading task pool
+[2026-01-08 04:49:09,773][fusion_bench.method.classification.image_classification_finetune][INFO] - Number of classes for dataset dtd: 47
+[2026-01-08 04:49:09,786][datasets.load][WARNING] - Using the latest cached version of the dataset since tanganke/dtd couldn't be found on the Hugging Face Hub (offline mode is enabled).
+[2026-01-08 04:49:09,795][datasets.packaged_modules.cache.cache][WARNING] - Found the latest cached dataset configuration 'default' at /data/dataset/datasets/tanganke___dtd/default/0.0.0/d2afa97d9f335b1a6b3b09c637aef667f98f966e (last modified on Mon Jan  5 04:22:16 2026).
+[2026-01-08 04:49:09,972][fusion_bench.method.classification.image_classification_finetune][INFO] - Training dataset size: 3760
+[2026-01-08 04:49:10,003][datasets.load][WARNING] - Using the latest cached version of the dataset since tanganke/dtd couldn't be found on the Hugging Face Hub (offline mode is enabled).
+[2026-01-08 04:49:10,010][datasets.packaged_modules.cache.cache][WARNING] - Found the latest cached dataset configuration 'default' at /data/dataset/datasets/tanganke___dtd/default/0.0.0/d2afa97d9f335b1a6b3b09c637aef667f98f966e (last modified on Mon Jan  5 04:22:16 2026).
+[2026-01-08 04:49:10,060][fusion_bench.method.classification.image_classification_finetune][INFO] - optimizer:
+SGD (
+Parameter Group 0
+    dampening: 0
+    differentiable: False
+    foreach: None
+    fused: None
+    lr: 0.01
+    maximize: False
+    momentum: 0.9
+    nesterov: False
+    weight_decay: 0.0001
+)
+[2026-01-08 05:15:05,827][fusion_bench.method.classification.image_classification_finetune][INFO] - Saving the final model to outputs/convnext-base-224/dtd/batch_size=64,lr=0.01/raw_checkpoints/final

config.json

@@ -0,0 +1,140 @@
+{
+  "architectures": [
+    "ConvNextForImageClassification"
+  ],
+  "depths": [
+    3,
+    3,
+    27,
+    3
+  ],
+  "drop_path_rate": 0.0,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_sizes": [
+    128,
+    256,
+    512,
+    1024
+  ],
+  "id2label": {
+    "0": "banded",
+    "1": "blotchy",
+    "2": "braided",
+    "3": "bubbly",
+    "4": "bumpy",
+    "5": "chequered",
+    "6": "cobwebbed",
+    "7": "cracked",
+    "8": "crosshatched",
+    "9": "crystalline",
+    "10": "dotted",
+    "11": "fibrous",
+    "12": "flecked",
+    "13": "freckled",
+    "14": "frilly",
+    "15": "gauzy",
+    "16": "grid",
+    "17": "grooved",
+    "18": "honeycombed",
+    "19": "interlaced",
+    "20": "knitted",
+    "21": "lacelike",
+    "22": "lined",
+    "23": "marbled",
+    "24": "matted",
+    "25": "meshed",
+    "26": "paisley",
+    "27": "perforated",
+    "28": "pitted",
+    "29": "pleated",
+    "30": "polka-dotted",
+    "31": "porous",
+    "32": "potholed",
+    "33": "scaly",
+    "34": "smeared",
+    "35": "spiralled",
+    "36": "sprinkled",
+    "37": "stained",
+    "38": "stratified",
+    "39": "striped",
+    "40": "studded",
+    "41": "swirly",
+    "42": "veined",
+    "43": "waffled",
+    "44": "woven",
+    "45": "wrinkled",
+    "46": "zigzagged"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "banded": 0,
+    "blotchy": 1,
+    "braided": 2,
+    "bubbly": 3,
+    "bumpy": 4,
+    "chequered": 5,
+    "cobwebbed": 6,
+    "cracked": 7,
+    "crosshatched": 8,
+    "crystalline": 9,
+    "dotted": 10,
+    "fibrous": 11,
+    "flecked": 12,
+    "freckled": 13,
+    "frilly": 14,
+    "gauzy": 15,
+    "grid": 16,
+    "grooved": 17,
+    "honeycombed": 18,
+    "interlaced": 19,
+    "knitted": 20,
+    "lacelike": 21,
+    "lined": 22,
+    "marbled": 23,
+    "matted": 24,
+    "meshed": 25,
+    "paisley": 26,
+    "perforated": 27,
+    "pitted": 28,
+    "pleated": 29,
+    "polka-dotted": 30,
+    "porous": 31,
+    "potholed": 32,
+    "scaly": 33,
+    "smeared": 34,
+    "spiralled": 35,
+    "sprinkled": 36,
+    "stained": 37,
+    "stratified": 38,
+    "striped": 39,
+    "studded": 40,
+    "swirly": 41,
+    "veined": 42,
+    "waffled": 43,
+    "woven": 44,
+    "wrinkled": 45,
+    "zigzagged": 46
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_scale_init_value": 1e-06,
+  "model_type": "convnext",
+  "num_channels": 3,
+  "num_stages": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "transformers_version": "4.57.3"
+}

config.yaml

@@ -0,0 +1,58 @@
+path:
+  root_dir: ${oc.env:FUSION_BENCH_PROJECT_ROOT,"."}
+  output_dir: ${.root_dir}/outputs
+  data_dir: ${oc.env:FUSION_BENCH_DATA_DIR,${.root_dir}/data}
+  cache_dir: ${oc.env:FUSION_BENCH_CACHE_DIR,${.output_dir}/cache}
+  log_dir: outputs/convnext-base-224/dtd/batch_size=64,lr=0.01
+  work_dir: ${hydra:runtime.cwd}
+modelpool:
+  _target_: fusion_bench.modelpool.ConvNextForImageClassificationPool
+  _recursive_: false
+  models:
+    _pretrained_:
+      config_path: facebook/convnext-base-224
+      pretrained: true
+      dataset_name: dtd
+  train_datasets:
+    dtd:
+      _target_: datasets.load_dataset
+      path: tanganke/dtd
+      split: train
+  val_datasets:
+    dtd:
+      _target_: datasets.load_dataset
+      path: tanganke/dtd
+      split: test
+  test_datasets: null
+method:
+  _target_: fusion_bench.method.classification.ImageClassificationFineTuning
+  max_epochs: -1
+  max_steps: 4000
+  save_top_k: -1
+  save_interval: 1000
+  save_on_train_epoch_end: false
+  training_data_ratio: null
+  label_smoothing: 0
+  optimizer:
+    _target_: torch.optim.SGD
+    lr: 0.01
+    momentum: 0.9
+    weight_decay: 0.0001
+  lr_scheduler: null
+  dataloader_kwargs:
+    batch_size: 64
+    num_workers: 8
+    pin_memory: true
+taskpool:
+  _target_: fusion_bench.taskpool.DummyTaskPool
+  model_save_path: null
+_target_: fusion_bench.programs.ModelFusionProgram
+_recursive_: false
+seed: 0
+fast_dev_run: false
+dry_run: false
+print_config: true
+print_function_call: true
+merged_model_save_path: null
+merged_model_save_kwargs: null
+report_save_path: '{log_dir}/program_report.json'

events.out.tfevents.1767847750.pt-b7552130803b44b59bdfb04f6bb732f9-worker-0.9570.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adf1cf9367b11a86f35bfe5c39cb8326912d171422dff57d863ae1a1aad7f2d9
+size 2104473

hparams.yaml

@@ -0,0 +1 @@
+{}

hydra.yaml

@@ -0,0 +1,208 @@
+hydra:
+  run:
+    dir: ${path.log_dir}
+  sweep:
+    dir: ${oc.env:FUSION_BENCH_PROJECT_ROOT,"."}/outputs/multirun/${hydra.job.config_name}/${now:%Y-%m-%d_%H-%M-%S}
+    subdir: ${hydra.job.num}
+  launcher:
+    _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
+  sweeper:
+    _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
+    max_batch_size: null
+    params: null
+  help:
+    app_name: fusion_bench
+    header: == ${hydra.help.app_name} ==
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help'
+    template: '${hydra.help.header}
+
+
+      fusion_bench is the command line interface for running model fusion benchmarks
+      in the FusionBench project.
+
+      It provides a flexible way to configure and execute various fusion algorithms
+      on different model pools and evaluate them across multiple tasks.
+
+
+      == Configuration groups ==
+
+      Compose your configuration from these groups (method, modelpool, taskpool are
+      the most important):
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      You can override options, for example:
+
+      fusion_bench method=task_arithmetic modelpool=clip-vit-base-patch32_svhn_and_mnist
+      taskpool=clip-vit-base-patch32_svhn_and_mnist
+
+
+      == Basic usage ==
+
+      fusion_bench [--config-path CONFIG_PATH] [--config-name CONFIG_NAME] OPTION_1=VALUE_1
+      OPTION_2=VALUE_2 ...
+
+
+      == Key options ==
+
+      --help, -h            : Print this help message and exit
+
+      --hydra-help          : Hydra''s help
+
+      --cfg, -c             : Show config instead of running [job|hydra|all]
+
+      --config-path, -cp    : Overrides the config_path
+
+      --config-name, -cn    : Overrides the config_name
+
+      --shell-completion, -sc : Install or Uninstall shell completion
+
+
+      For more detailed information on options and usage, please refer to the online
+      documentation:
+
+      https://tanganke.github.io/fusion_bench/cli/fusion_bench/
+
+
+      ${hydra.help.footer}'
+  hydra_help:
+    template: 'Hydra (${hydra.runtime.version})
+
+      See https://hydra.cc for more info.
+
+
+      == Flags ==
+
+      $FLAGS_HELP
+
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (For example, append hydra/job_logging=disabled
+      to command line)
+
+
+      $HYDRA_CONFIG_GROUPS
+
+
+      Use ''--cfg hydra'' to Show the Hydra config.
+
+      '
+    hydra_help: ???
+  hydra_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][HYDRA] %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+    root:
+      level: INFO
+      handlers:
+      - console
+    loggers:
+      logging_example:
+        level: DEBUG
+    disable_existing_loggers: false
+  job_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
+      rich_handler:
+        format: '%(message)s'
+    handlers:
+      console:
+        class: rich.logging.RichHandler
+        formatter: rich_handler
+      file:
+        class: logging.FileHandler
+        formatter: simple
+        filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks: {}
+  output_subdir: ''
+  overrides:
+    hydra:
+    - hydra.mode=RUN
+    task:
+    - path.log_dir="outputs/convnext-base-224/dtd/batch_size=64,lr=0.01"
+    - seed=0
+    - method=classification/image_classification_finetune
+    - method.max_epochs=-1
+    - method.max_steps=4000
+    - method.save_top_k=-1
+    - method.save_interval=1000
+    - method.save_on_train_epoch_end=false
+    - method.optimizer.lr=0.01
+    - method.lr_scheduler=null
+    - method.dataloader_kwargs.batch_size=64
+    - modelpool=ConvNextForImageClassification/convnext-base-224
+    - modelpool.models._pretrained_.dataset_name=dtd
+    - +dataset/image_classification/train@modelpool.train_datasets=dtd
+    - +dataset/image_classification/test@modelpool.val_datasets=dtd
+  job:
+    name: cli
+    chdir: null
+    override_dirname: +dataset/image_classification/test@modelpool.val_datasets=dtd,+dataset/image_classification/train@modelpool.train_datasets=dtd,method.dataloader_kwargs.batch_size=64,method.lr_scheduler=null,method.max_epochs=-1,method.max_steps=4000,method.optimizer.lr=0.01,method.save_interval=1000,method.save_on_train_epoch_end=false,method.save_top_k=-1,method=classification/image_classification_finetune,modelpool.models._pretrained_.dataset_name=dtd,modelpool=ConvNextForImageClassification/convnext-base-224,path.log_dir="outputs/convnext-base-224/dtd/batch_size=64,lr=0.01",seed=0
+    id: ???
+    num: ???
+    config_name: model_fusion
+    env_set:
+      HYDRA_FULL_ERROR: ${oc.env:HYDRA_FULL_ERROR,1}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.3.2
+    version_base: '1.3'
+    cwd: /data/users/anke/fusion_bench
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /data/users/anke/fusion_bench/config
+      schema: file
+      provider: main
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /data/users/anke/fusion_bench/outputs/convnext-base-224/dtd/batch_size=64,lr=0.01
+    choices:
+      dataset/image_classification/test@modelpool.val_datasets: dtd
+      dataset/image_classification/train@modelpool.train_datasets: dtd
+      taskpool: dummy
+      method: classification/image_classification_finetune
+      modelpool: ConvNextForImageClassification/convnext-base-224
+      path: default
+      hydra: default
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: rich_logging
+      hydra/hydra_logging: default
+      hydra/hydra_help: default
+      hydra/help: fusion_bench_help
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09f8d857a3c336c72c9a38f43bc92b9d715a44f200f7e4bb9a2e7080d2cbe98c
+size 350499748

overrides.yaml

@@ -0,0 +1,15 @@
+- path.log_dir="outputs/convnext-base-224/dtd/batch_size=64,lr=0.01"
+- seed=0
+- method=classification/image_classification_finetune
+- method.max_epochs=-1
+- method.max_steps=4000
+- method.save_top_k=-1
+- method.save_interval=1000
+- method.save_on_train_epoch_end=false
+- method.optimizer.lr=0.01
+- method.lr_scheduler=null
+- method.dataloader_kwargs.batch_size=64
+- modelpool=ConvNextForImageClassification/convnext-base-224
+- modelpool.models._pretrained_.dataset_name=dtd
+- +dataset/image_classification/train@modelpool.train_datasets=dtd
+- +dataset/image_classification/test@modelpool.val_datasets=dtd

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "crop_pct": 0.875,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ConvNextImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

program_report.json

@@ -0,0 +1 @@
+{"model_info": {"trainable_params": 87614639, "all_params": 87614639, "trainable_percentage": 1.0}}