Upload XmodForSequenceClassification

README.md

@@ -0,0 +1,201 @@
+---
+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 +1,123 @@
+{
+  "_name_or_path": "kangXn/enhi-tp",
+  "adapter_layer_norm": false,
+  "adapter_reduction_factor": 2,
+  "adapter_reuse_layer_norm": true,
+  "architectures": [
+    "XmodForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "default_language": "hi_IN",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "languages": [
+    "en_XX",
+    "id_ID",
+    "vi_VN",
+    "ru_RU",
+    "fa_IR",
+    "sv_SE",
+    "ja_XX",
+    "fr_XX",
+    "de_DE",
+    "ro_RO",
+    "ko_KR",
+    "hu_HU",
+    "es_XX",
+    "fi_FI",
+    "uk_UA",
+    "da_DK",
+    "pt_XX",
+    "no_XX",
+    "th_TH",
+    "pl_PL",
+    "bg_BG",
+    "nl_XX",
+    "zh_CN",
+    "he_IL",
+    "el_GR",
+    "it_IT",
+    "sk_SK",
+    "hr_HR",
+    "tr_TR",
+    "ar_AR",
+    "cs_CZ",
+    "lt_LT",
+    "hi_IN",
+    "zh_TW",
+    "ca_ES",
+    "ms_MY",
+    "sl_SI",
+    "lv_LV",
+    "ta_IN",
+    "bn_IN",
+    "et_EE",
+    "az_AZ",
+    "sq_AL",
+    "sr_RS",
+    "kk_KZ",
+    "ka_GE",
+    "tl_XX",
+    "ur_PK",
+    "is_IS",
+    "hy_AM",
+    "ml_IN",
+    "mk_MK",
+    "be_BY",
+    "la_VA",
+    "te_IN",
+    "eu_ES",
+    "gl_ES",
+    "mn_MN",
+    "kn_IN",
+    "ne_NP",
+    "sw_KE",
+    "si_LK",
+    "mr_IN",
+    "af_ZA",
+    "gu_IN",
+    "cy_GB",
+    "eo_EO",
+    "km_KH",
+    "ky_KG",
+    "uz_UZ",
+    "ps_AF",
+    "pa_IN",
+    "ga_IE",
+    "ha_NG",
+    "am_ET",
+    "lo_LA",
+    "ku_TR",
+    "so_SO",
+    "my_MM",
+    "or_IN",
+    "sa_IN"
+  ],
+  "layer_norm_eps": 1e-05,
+  "ln_before_adapter": true,
+  "max_position_embeddings": 514,
+  "model_type": "xmod",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "pre_norm": false,
+  "problem_type": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad5d98cfca67028aa739e1662b3d971ce92c7c258c4bed6aa93994ee392f050
+size 3410454016