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 +1,433 @@
+{
+  "_name_or_path": "results/checkpoint-42598",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "lit_Latn",
+    "1": "fon_Latn",
+    "2": "kin_Latn",
+    "3": "khm_Khmr",
+    "4": "bjn_Latn",
+    "5": "prs_Arab",
+    "6": "wol_Latn",
+    "7": "run_Latn",
+    "8": "eng_Latn",
+    "9": "gla_Latn",
+    "10": "lvs_Latn",
+    "11": "nya_Latn",
+    "12": "kac_Latn",
+    "13": "lua_Latn",
+    "14": "tuk_Latn",
+    "15": "tpi_Latn",
+    "16": "grn_Latn",
+    "17": "xho_Latn",
+    "18": "bam_Latn",
+    "19": "mri_Latn",
+    "20": "san_Deva",
+    "21": "isl_Latn",
+    "22": "kas_Deva",
+    "23": "bel_Cyrl",
+    "24": "heb_Hebr",
+    "25": "zho_Hant",
+    "26": "bak_Cyrl",
+    "27": "fra_Latn",
+    "28": "por_Latn",
+    "29": "ukr_Cyrl",
+    "30": "umb_Latn",
+    "31": "kan_Knda",
+    "32": "smo_Latn",
+    "33": "als_Latn",
+    "34": "kbp_Latn",
+    "35": "lin_Latn",
+    "36": "urd_Arab",
+    "37": "yor_Latn",
+    "38": "azb_Arab",
+    "39": "ltz_Latn",
+    "40": "twi_Latn",
+    "41": "hin_Deva",
+    "42": "tgl_Latn",
+    "43": "asm_Beng",
+    "44": "gaz_Latn",
+    "45": "ell_Grek",
+    "46": "taq_Tfng",
+    "47": "nso_Latn",
+    "48": "dan_Latn",
+    "49": "pes_Arab",
+    "50": "pan_Guru",
+    "51": "war_Latn",
+    "52": "mar_Deva",
+    "53": "mni_Beng",
+    "54": "acm_Arab",
+    "55": "srd_Latn",
+    "56": "vec_Latn",
+    "57": "ory_Orya",
+    "58": "lug_Latn",
+    "59": "ltg_Latn",
+    "60": "guj_Gujr",
+    "61": "ita_Latn",
+    "62": "swe_Latn",
+    "63": "cjk_Latn",
+    "64": "ace_Latn",
+    "65": "taq_Latn",
+    "66": "cat_Latn",
+    "67": "zsm_Latn",
+    "68": "hun_Latn",
+    "69": "kaz_Cyrl",
+    "70": "pol_Latn",
+    "71": "ban_Latn",
+    "72": "nus_Latn",
+    "73": "acq_Arab",
+    "74": "aeb_Arab",
+    "75": "spa_Latn",
+    "76": "slk_Latn",
+    "77": "hrv_Latn",
+    "78": "crh_Latn",
+    "79": "tur_Latn",
+    "80": "bos_Latn",
+    "81": "ssw_Latn",
+    "82": "kik_Latn",
+    "83": "ydd_Hebr",
+    "84": "snd_Arab",
+    "85": "hau_Latn",
+    "86": "tam_Taml",
+    "87": "plt_Latn",
+    "88": "kmr_Latn",
+    "89": "ace_Arab",
+    "90": "mkd_Cyrl",
+    "91": "lij_Latn",
+    "92": "dyu_Latn",
+    "93": "mos_Latn",
+    "94": "ayr_Latn",
+    "95": "ast_Latn",
+    "96": "fij_Latn",
+    "97": "lmo_Latn",
+    "98": "zho_Hans",
+    "99": "nob_Latn",
+    "100": "hye_Armn",
+    "101": "amh_Ethi",
+    "102": "jav_Latn",
+    "103": "sag_Latn",
+    "104": "mai_Deva",
+    "105": "lao_Laoo",
+    "106": "uzn_Latn",
+    "107": "mya_Mymr",
+    "108": "fin_Latn",
+    "109": "knc_Latn",
+    "110": "tat_Cyrl",
+    "111": "ajp_Arab",
+    "112": "dzo_Tibt",
+    "113": "pag_Latn",
+    "114": "kir_Cyrl",
+    "115": "sna_Latn",
+    "116": "zul_Latn",
+    "117": "kab_Latn",
+    "118": "fur_Latn",
+    "119": "ckb_Arab",
+    "120": "vie_Latn",
+    "121": "mal_Mlym",
+    "122": "bem_Latn",
+    "123": "som_Latn",
+    "124": "ars_Arab",
+    "125": "szl_Latn",
+    "126": "tgk_Cyrl",
+    "127": "tel_Telu",
+    "128": "quy_Latn",
+    "129": "deu_Latn",
+    "130": "bjn_Arab",
+    "131": "azj_Latn",
+    "132": "eus_Latn",
+    "133": "ces_Latn",
+    "134": "nld_Latn",
+    "135": "shn_Mymr",
+    "136": "bul_Cyrl",
+    "137": "kam_Latn",
+    "138": "kmb_Latn",
+    "139": "ron_Latn",
+    "140": "bho_Deva",
+    "141": "glg_Latn",
+    "142": "awa_Deva",
+    "143": "tha_Thai",
+    "144": "lim_Latn",
+    "145": "hat_Latn",
+    "146": "mag_Deva",
+    "147": "kon_Latn",
+    "148": "pbt_Arab",
+    "149": "kat_Geor",
+    "150": "khk_Cyrl",
+    "151": "arb_Arab",
+    "152": "knc_Arab",
+    "153": "kor_Hang",
+    "154": "oci_Latn",
+    "155": "lus_Latn",
+    "156": "ary_Arab",
+    "157": "epo_Latn",
+    "158": "pap_Latn",
+    "159": "ibo_Latn",
+    "160": "fao_Latn",
+    "161": "ben_Beng",
+    "162": "yue_Hant",
+    "163": "ceb_Latn",
+    "164": "luo_Latn",
+    "165": "srp_Cyrl",
+    "166": "ind_Latn",
+    "167": "slv_Latn",
+    "168": "min_Latn",
+    "169": "scn_Latn",
+    "170": "apc_Arab",
+    "171": "sin_Sinh",
+    "172": "mlt_Latn",
+    "173": "kea_Latn",
+    "174": "uig_Arab",
+    "175": "npi_Deva",
+    "176": "kas_Arab",
+    "177": "bug_Latn",
+    "178": "hne_Deva",
+    "179": "sat_Olck",
+    "180": "swh_Latn",
+    "181": "tso_Latn",
+    "182": "nno_Latn",
+    "183": "rus_Cyrl",
+    "184": "dik_Latn",
+    "185": "sun_Latn",
+    "186": "afr_Latn",
+    "187": "arz_Arab",
+    "188": "gle_Latn",
+    "189": "sot_Latn",
+    "190": "ewe_Latn",
+    "191": "fuv_Latn",
+    "192": "tum_Latn",
+    "193": "ilo_Latn",
+    "194": "cym_Latn",
+    "195": "tir_Ethi",
+    "196": "tzm_Tfng",
+    "197": "bod_Tibt",
+    "198": "tsn_Latn",
+    "199": "est_Latn",
+    "200": "jpn_Jpan"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 768,
+  "label2id": {
+    "ace_Arab": 89,
+    "ace_Latn": 64,
+    "acm_Arab": 54,
+    "acq_Arab": 73,
+    "aeb_Arab": 74,
+    "afr_Latn": 186,
+    "ajp_Arab": 111,
+    "als_Latn": 33,
+    "amh_Ethi": 101,
+    "apc_Arab": 170,
+    "arb_Arab": 151,
+    "ars_Arab": 124,
+    "ary_Arab": 156,
+    "arz_Arab": 187,
+    "asm_Beng": 43,
+    "ast_Latn": 95,
+    "awa_Deva": 142,
+    "ayr_Latn": 94,
+    "azb_Arab": 38,
+    "azj_Latn": 131,
+    "bak_Cyrl": 26,
+    "bam_Latn": 18,
+    "ban_Latn": 71,
+    "bel_Cyrl": 23,
+    "bem_Latn": 122,
+    "ben_Beng": 161,
+    "bho_Deva": 140,
+    "bjn_Arab": 130,
+    "bjn_Latn": 4,
+    "bod_Tibt": 197,
+    "bos_Latn": 80,
+    "bug_Latn": 177,
+    "bul_Cyrl": 136,
+    "cat_Latn": 66,
+    "ceb_Latn": 163,
+    "ces_Latn": 133,
+    "cjk_Latn": 63,
+    "ckb_Arab": 119,
+    "crh_Latn": 78,
+    "cym_Latn": 194,
+    "dan_Latn": 48,
+    "deu_Latn": 129,
+    "dik_Latn": 184,
+    "dyu_Latn": 92,
+    "dzo_Tibt": 112,
+    "ell_Grek": 45,
+    "eng_Latn": 8,
+    "epo_Latn": 157,
+    "est_Latn": 199,
+    "eus_Latn": 132,
+    "ewe_Latn": 190,
+    "fao_Latn": 160,
+    "fij_Latn": 96,
+    "fin_Latn": 108,
+    "fon_Latn": 1,
+    "fra_Latn": 27,
+    "fur_Latn": 118,
+    "fuv_Latn": 191,
+    "gaz_Latn": 44,
+    "gla_Latn": 9,
+    "gle_Latn": 188,
+    "glg_Latn": 141,
+    "grn_Latn": 16,
+    "guj_Gujr": 60,
+    "hat_Latn": 145,
+    "hau_Latn": 85,
+    "heb_Hebr": 24,
+    "hin_Deva": 41,
+    "hne_Deva": 178,
+    "hrv_Latn": 77,
+    "hun_Latn": 68,
+    "hye_Armn": 100,
+    "ibo_Latn": 159,
+    "ilo_Latn": 193,
+    "ind_Latn": 166,
+    "isl_Latn": 21,
+    "ita_Latn": 61,
+    "jav_Latn": 102,
+    "jpn_Jpan": 200,
+    "kab_Latn": 117,
+    "kac_Latn": 12,
+    "kam_Latn": 137,
+    "kan_Knda": 31,
+    "kas_Arab": 176,
+    "kas_Deva": 22,
+    "kat_Geor": 149,
+    "kaz_Cyrl": 69,
+    "kbp_Latn": 34,
+    "kea_Latn": 173,
+    "khk_Cyrl": 150,
+    "khm_Khmr": 3,
+    "kik_Latn": 82,
+    "kin_Latn": 2,
+    "kir_Cyrl": 114,
+    "kmb_Latn": 138,
+    "kmr_Latn": 88,
+    "knc_Arab": 152,
+    "knc_Latn": 109,
+    "kon_Latn": 147,
+    "kor_Hang": 153,
+    "lao_Laoo": 105,
+    "lij_Latn": 91,
+    "lim_Latn": 144,
+    "lin_Latn": 35,
+    "lit_Latn": 0,
+    "lmo_Latn": 97,
+    "ltg_Latn": 59,
+    "ltz_Latn": 39,
+    "lua_Latn": 13,
+    "lug_Latn": 58,
+    "luo_Latn": 164,
+    "lus_Latn": 155,
+    "lvs_Latn": 10,
+    "mag_Deva": 146,
+    "mai_Deva": 104,
+    "mal_Mlym": 121,
+    "mar_Deva": 52,
+    "min_Latn": 168,
+    "mkd_Cyrl": 90,
+    "mlt_Latn": 172,
+    "mni_Beng": 53,
+    "mos_Latn": 93,
+    "mri_Latn": 19,
+    "mya_Mymr": 107,
+    "nld_Latn": 134,
+    "nno_Latn": 182,
+    "nob_Latn": 99,
+    "npi_Deva": 175,
+    "nso_Latn": 47,
+    "nus_Latn": 72,
+    "nya_Latn": 11,
+    "oci_Latn": 154,
+    "ory_Orya": 57,
+    "pag_Latn": 113,
+    "pan_Guru": 50,
+    "pap_Latn": 158,
+    "pbt_Arab": 148,
+    "pes_Arab": 49,
+    "plt_Latn": 87,
+    "pol_Latn": 70,
+    "por_Latn": 28,
+    "prs_Arab": 5,
+    "quy_Latn": 128,
+    "ron_Latn": 139,
+    "run_Latn": 7,
+    "rus_Cyrl": 183,
+    "sag_Latn": 103,
+    "san_Deva": 20,
+    "sat_Olck": 179,
+    "scn_Latn": 169,
+    "shn_Mymr": 135,
+    "sin_Sinh": 171,
+    "slk_Latn": 76,
+    "slv_Latn": 167,
+    "smo_Latn": 32,
+    "sna_Latn": 115,
+    "snd_Arab": 84,
+    "som_Latn": 123,
+    "sot_Latn": 189,
+    "spa_Latn": 75,
+    "srd_Latn": 55,
+    "srp_Cyrl": 165,
+    "ssw_Latn": 81,
+    "sun_Latn": 185,
+    "swe_Latn": 62,
+    "swh_Latn": 180,
+    "szl_Latn": 125,
+    "tam_Taml": 86,
+    "taq_Latn": 65,
+    "taq_Tfng": 46,
+    "tat_Cyrl": 110,
+    "tel_Telu": 127,
+    "tgk_Cyrl": 126,
+    "tgl_Latn": 42,
+    "tha_Thai": 143,
+    "tir_Ethi": 195,
+    "tpi_Latn": 15,
+    "tsn_Latn": 198,
+    "tso_Latn": 181,
+    "tuk_Latn": 14,
+    "tum_Latn": 192,
+    "tur_Latn": 79,
+    "twi_Latn": 40,
+    "tzm_Tfng": 196,
+    "uig_Arab": 174,
+    "ukr_Cyrl": 29,
+    "umb_Latn": 30,
+    "urd_Arab": 36,
+    "uzn_Latn": 106,
+    "vec_Latn": 56,
+    "vie_Latn": 120,
+    "war_Latn": 51,
+    "wol_Latn": 6,
+    "xho_Latn": 17,
+    "ydd_Hebr": 83,
+    "yor_Latn": 37,
+    "yue_Hant": 162,
+    "zho_Hans": 98,
+    "zho_Hant": 25,
+    "zsm_Latn": 67,
+    "zul_Latn": 116
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 4,
+  "pad_token_id": 3,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a334ced506aa854d8611bb73aab490adb476ba79ea1b40f816156415012a668d
+size 97838484