Upload RobertaForSequenceClassification

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 +1,258 @@
+{
+  "_name_or_path": "pjox/dalembert",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "perronet",
+    "1": "boucher",
+    "2": "pestre",
+    "3": "authville",
+    "4": "petit",
+    "5": "damilaville",
+    "6": "rousseau",
+    "7": "bouchaud",
+    "8": "anville",
+    "9": "aumont",
+    "10": "barthez_de_marmorieres",
+    "11": "fouquet",
+    "12": "ratte",
+    "13": "venel",
+    "14": "kurdwanowski",
+    "15": "meyzieu",
+    "16": "lacondamine",
+    "17": "tressan",
+    "18": "boullanger",
+    "19": "dalembert",
+    "20": "beauzee",
+    "21": "robert",
+    "22": "faiguet",
+    "23": "soubeyran",
+    "24": "voglie",
+    "25": "deleyre",
+    "26": "leromain",
+    "27": "naigeon",
+    "28": "desmahis",
+    "29": "malouin",
+    "30": "quesnay",
+    "31": "dumarsais",
+    "32": "watelet",
+    "33": "tronchin",
+    "34": "dufour",
+    "35": "genson",
+    "36": "leroy_cg",
+    "37": "argenville",
+    "38": "lavirotte",
+    "39": "lemonnier",
+    "40": "leblond",
+    "41": "eidous",
+    "42": "sauvages",
+    "43": "millot",
+    "44": "grosley",
+    "45": "morellet",
+    "46": "forbonnais",
+    "47": "romilly_j",
+    "48": "blondel",
+    "49": "diderot",
+    "50": "duclos",
+    "51": "grimm",
+    "52": "bordeu",
+    "53": "david",
+    "54": "lesage",
+    "55": "bellin",
+    "56": "lefevre",
+    "57": "toussaint",
+    "58": "lebreton",
+    "59": "bertrand",
+    "60": "falconet",
+    "61": "lachapelle",
+    "62": "landois",
+    "63": "bouchu",
+    "64": "montet",
+    "65": "monnoye",
+    "66": "collot",
+    "67": "montdorge",
+    "68": "morand",
+    "69": "holbach",
+    "70": "berthoud",
+    "71": "barthez",
+    "72": "willermoz",
+    "73": "louis",
+    "74": "menuret",
+    "75": "necker",
+    "76": "papillon",
+    "77": "roux",
+    "78": "bouillet_j",
+    "79": "margency",
+    "80": "bourgelat",
+    "81": "brisson",
+    "82": "daubenton_p",
+    "83": "paillasson",
+    "84": "pezay",
+    "85": "yvon",
+    "86": "durival_j",
+    "87": "goussier",
+    "88": "daubenton_ljm",
+    "89": "jaucourt",
+    "90": "gueneau",
+    "91": "abbes",
+    "92": "fenouillot",
+    "93": "lenglet",
+    "94": "formey",
+    "95": "marmontel",
+    "96": "lamotte",
+    "97": "tarin",
+    "98": "liebault",
+    "99": "pesselier",
+    "100": "allut",
+    "101": "vandenesse",
+    "102": "mallet",
+    "103": "lucotte_jr",
+    "104": "romilly_je",
+    "105": "penchenier",
+    "106": "brulle",
+    "107": "desmarest",
+    "108": "cahusac",
+    "109": "voltaire",
+    "110": "villiers",
+    "111": "leroy_jb",
+    "112": "rallier"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "abbes": 91,
+    "allut": 100,
+    "anville": 8,
+    "argenville": 37,
+    "aumont": 9,
+    "authville": 3,
+    "barthez": 71,
+    "barthez_de_marmorieres": 10,
+    "beauzee": 20,
+    "bellin": 55,
+    "berthoud": 70,
+    "bertrand": 59,
+    "blondel": 48,
+    "bordeu": 52,
+    "bouchaud": 7,
+    "boucher": 1,
+    "bouchu": 63,
+    "bouillet_j": 78,
+    "boullanger": 18,
+    "bourgelat": 80,
+    "brisson": 81,
+    "brulle": 106,
+    "cahusac": 108,
+    "collot": 66,
+    "dalembert": 19,
+    "damilaville": 5,
+    "daubenton_ljm": 88,
+    "daubenton_p": 82,
+    "david": 53,
+    "deleyre": 25,
+    "desmahis": 28,
+    "desmarest": 107,
+    "diderot": 49,
+    "duclos": 50,
+    "dufour": 34,
+    "dumarsais": 31,
+    "durival_j": 86,
+    "eidous": 41,
+    "faiguet": 22,
+    "falconet": 60,
+    "fenouillot": 92,
+    "forbonnais": 46,
+    "formey": 94,
+    "fouquet": 11,
+    "genson": 35,
+    "goussier": 87,
+    "grimm": 51,
+    "grosley": 44,
+    "gueneau": 90,
+    "holbach": 69,
+    "jaucourt": 89,
+    "kurdwanowski": 14,
+    "lachapelle": 61,
+    "lacondamine": 16,
+    "lamotte": 96,
+    "landois": 62,
+    "lavirotte": 38,
+    "leblond": 40,
+    "lebreton": 58,
+    "lefevre": 56,
+    "lemonnier": 39,
+    "lenglet": 93,
+    "leromain": 26,
+    "leroy_cg": 36,
+    "leroy_jb": 111,
+    "lesage": 54,
+    "liebault": 98,
+    "louis": 73,
+    "lucotte_jr": 103,
+    "mallet": 102,
+    "malouin": 29,
+    "margency": 79,
+    "marmontel": 95,
+    "menuret": 74,
+    "meyzieu": 15,
+    "millot": 43,
+    "monnoye": 65,
+    "montdorge": 67,
+    "montet": 64,
+    "morand": 68,
+    "morellet": 45,
+    "naigeon": 27,
+    "necker": 75,
+    "paillasson": 83,
+    "papillon": 76,
+    "penchenier": 105,
+    "perronet": 0,
+    "pesselier": 99,
+    "pestre": 2,
+    "petit": 4,
+    "pezay": 84,
+    "quesnay": 30,
+    "rallier": 112,
+    "ratte": 12,
+    "robert": 21,
+    "romilly_j": 47,
+    "romilly_je": 104,
+    "rousseau": 6,
+    "roux": 77,
+    "sauvages": 42,
+    "soubeyran": 23,
+    "tarin": 97,
+    "toussaint": 57,
+    "tressan": 17,
+    "tronchin": 33,
+    "vandenesse": 101,
+    "venel": 13,
+    "villiers": 110,
+    "voglie": 24,
+    "voltaire": 109,
+    "watelet": 32,
+    "willermoz": 72,
+    "yvon": 85
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32768
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02e0b99dbdeb828fca18e780916d43af6478917841bb2118a379c1a49b031242
+size 445203476