Upload BertForSequenceClassification

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 +1,179 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": 0.1,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "C00",
+    "1": "C01",
+    "2": "C02",
+    "3": "C05",
+    "4": "C06",
+    "5": "C07",
+    "6": "C08",
+    "7": "C09",
+    "8": "C10",
+    "9": "C11",
+    "10": "C12",
+    "11": "C13",
+    "12": "C15",
+    "13": "C16",
+    "14": "C17",
+    "15": "C18",
+    "16": "C19",
+    "17": "C20",
+    "18": "C21",
+    "19": "C22",
+    "20": "C23",
+    "21": "C24",
+    "22": "C25",
+    "23": "C30",
+    "24": "C31",
+    "25": "C32",
+    "26": "C33",
+    "27": "C34",
+    "28": "C37",
+    "29": "C38",
+    "30": "C40",
+    "31": "C41",
+    "32": "C44",
+    "33": "C45",
+    "34": "C46",
+    "35": "C48",
+    "36": "C49",
+    "37": "C50",
+    "38": "C51",
+    "39": "C52",
+    "40": "C53",
+    "41": "C56",
+    "42": "C57",
+    "43": "C60",
+    "44": "C61",
+    "45": "C62",
+    "46": "C64",
+    "47": "C65",
+    "48": "C66",
+    "49": "C67",
+    "50": "C68",
+    "51": "C69",
+    "52": "C71",
+    "53": "C73",
+    "54": "C74",
+    "55": "C75",
+    "56": "C76",
+    "57": "C81",
+    "58": "C82",
+    "59": "C83",
+    "60": "C84",
+    "61": "C85",
+    "62": "C86",
+    "63": "C88",
+    "64": "C90",
+    "65": "C91",
+    "66": "C92",
+    "67": "C93",
+    "68": "C94",
+    "69": "C95"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "C00": 0,
+    "C01": 1,
+    "C02": 2,
+    "C05": 3,
+    "C06": 4,
+    "C07": 5,
+    "C08": 6,
+    "C09": 7,
+    "C10": 8,
+    "C11": 9,
+    "C12": 10,
+    "C13": 11,
+    "C15": 12,
+    "C16": 13,
+    "C17": 14,
+    "C18": 15,
+    "C19": 16,
+    "C20": 17,
+    "C21": 18,
+    "C22": 19,
+    "C23": 20,
+    "C24": 21,
+    "C25": 22,
+    "C30": 23,
+    "C31": 24,
+    "C32": 25,
+    "C33": 26,
+    "C34": 27,
+    "C37": 28,
+    "C38": 29,
+    "C40": 30,
+    "C41": 31,
+    "C44": 32,
+    "C45": 33,
+    "C46": 34,
+    "C48": 35,
+    "C49": 36,
+    "C50": 37,
+    "C51": 38,
+    "C52": 39,
+    "C53": 40,
+    "C56": 41,
+    "C57": 42,
+    "C60": 43,
+    "C61": 44,
+    "C62": 45,
+    "C64": 46,
+    "C65": 47,
+    "C66": 48,
+    "C67": 49,
+    "C68": 50,
+    "C69": 51,
+    "C71": 52,
+    "C73": 53,
+    "C74": 54,
+    "C75": 55,
+    "C76": 56,
+    "C81": 57,
+    "C82": 58,
+    "C83": 59,
+    "C84": 60,
+    "C85": 61,
+    "C86": 62,
+    "C88": 63,
+    "C90": 64,
+    "C91": 65,
+    "C92": 66,
+    "C93": 67,
+    "C94": 68,
+    "C95": 69
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "problem_type": "multi_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 120138
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e013221e18d5f1847de28c220b15bf7d6cd0a51cf2b8ea15c25a5d30d83de664
+size 713468152