Upload config

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,23 @@
+{
+  "auto_map": {
+    "AutoConfig": "configuration_resnet.ResNet10Config"
+  },
+  "depths": [
+    1,
+    1,
+    1,
+    1
+  ],
+  "embedding_size": 64,
+  "hidden_act": "relu",
+  "hidden_sizes": [
+    64,
+    128,
+    256,
+    512
+  ],
+  "model_type": "resnet10",
+  "num_channels": 3,
+  "pooler": "avg",
+  "transformers_version": "4.48.1"
+}

configuration_resnet.py

@@ -0,0 +1,80 @@
+# coding=utf-8#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""ResNet model configuration"""
+
+
+from transformers import PretrainedConfig
+
+
+class ResNet10Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`ResNetModel`]. It is used to instantiate an
+    ResNet model according to the specified arguments, defining the model architecture. Instantiating a configuration
+    with the defaults will yield a similar configuration to that of the ResNet
+    [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) architecture.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+    Args:
+        num_channels (`int`, *optional*, defaults to 3):
+            The number of input channels.
+        embedding_size (`int`, *optional*, defaults to 64):
+            Dimensionality (hidden size) for the embedding layer.
+        hidden_sizes (`List[int]`, *optional*, defaults to `[256, 512, 1024, 2048]`):
+            Dimensionality (hidden size) at each stage.
+        depths (`List[int]`, *optional*, defaults to `[3, 4, 6, 3]`):
+            Depth (number of layers) for each stage.
+        layer_type (`str`, *optional*, defaults to `"bottleneck"`):
+            The layer to use, it can be either `"basic"` (used for smaller models, like resnet-18 or resnet-34) or
+            `"bottleneck"` (used for larger models like resnet-50 and above).
+        hidden_act (`str`, *optional*, defaults to `"relu"`):
+            The non-linear activation function in each block. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"`
+            are supported.
+        downsample_in_first_stage (`bool`, *optional*, defaults to `False`):
+            If `True`, the first stage will downsample the inputs using a `stride` of 2.
+
+    Example:
+    ```python
+    >>> from transformers import AutoConfig, AutoModel
+
+    >>> # Initializing a ResNet resnet-50 style configuration
+    >>> configuration = AutoConfig.from_pretrained("helper2424/resnet10")
+
+    >>> # Initializing a model (with random weights) from the resnet-50 style configuration
+    >>> model = AutoModel.from_pretrained("helper2424/resnet10")
+
+    >>> # Accessing the model configuration
+    >>> model.config = configuration
+    ```
+    """
+
+    model_type = "resnet10"
+
+    def __init__(
+        self,
+        num_channels=3,
+        embedding_size=64,
+        hidden_sizes=[64, 128, 256, 512],
+        depths=[1, 1, 1, 1],
+        hidden_act="relu",
+        pooler="avg",
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+        self.num_channels = num_channels
+        self.embedding_size = embedding_size
+        self.hidden_sizes = hidden_sizes
+        self.depths = depths
+        self.hidden_act = hidden_act
+        self.pooler = pooler