Upload RobertaForTokenClassification

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 +1,75 @@
+{
+  "_name_or_path": "vinai/phobert-large",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "M\u00e3 \u0111\u01a1n",
+    "1": "Kh\u1ed1i l\u01b0\u1ee3ng",
+    "2": "STK",
+    "3": "\u0110\u01a1n v\u1ecb \u0111o",
+    "4": "O",
+    "5": "S\u0110T",
+    "6": "S\u1ea3n ph\u1ea9m c\u1ee5 th\u1ec3",
+    "7": "Ti\u1ec1n",
+    "8": "CCCD - CMT",
+    "9": "T\u00ean ng\u01b0\u1eddi",
+    "10": "S\u1ea3n ph\u1ea9m tr\u1eebu t\u01b0\u1ee3ng",
+    "11": "Ph\u01b0\u01a1ng th\u1ee9c thanh to\u00e1n",
+    "12": "Ca",
+    "13": "Ng\u00e2n h\u00e0ng",
+    "14": "Ng\u00e0y",
+    "15": "\u0110\u1ecba ch\u1ec9 c\u1ee5 th\u1ec3",
+    "16": "Gi\u1edd",
+    "17": "Email",
+    "18": "Ng\u00e0y tr\u1eebu t\u01b0\u1ee3ng",
+    "19": "\u0110\u1ecba ch\u1ec9 tr\u1eebu t\u01b0\u1ee3ng",
+    "20": "S\u0110T tr\u1eebu t\u01b0\u1ee3ng"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "CCCD - CMT": 8,
+    "Ca": 12,
+    "Email": 17,
+    "Gi\u1edd": 16,
+    "Kh\u1ed1i l\u01b0\u1ee3ng": 1,
+    "M\u00e3 \u0111\u01a1n": 0,
+    "Ng\u00e0y": 14,
+    "Ng\u00e0y tr\u1eebu t\u01b0\u1ee3ng": 18,
+    "Ng\u00e2n h\u00e0ng": 13,
+    "O": 4,
+    "Ph\u01b0\u01a1ng th\u1ee9c thanh to\u00e1n": 11,
+    "STK": 2,
+    "S\u0110T": 5,
+    "S\u0110T tr\u1eebu t\u01b0\u1ee3ng": 20,
+    "S\u1ea3n ph\u1ea9m c\u1ee5 th\u1ec3": 6,
+    "S\u1ea3n ph\u1ea9m tr\u1eebu t\u01b0\u1ee3ng": 10,
+    "Ti\u1ec1n": 7,
+    "T\u00ean ng\u01b0\u1eddi": 9,
+    "\u0110\u01a1n v\u1ecb \u0111o": 3,
+    "\u0110\u1ecba ch\u1ec9 c\u1ee5 th\u1ec3": 15,
+    "\u0110\u1ecba ch\u1ec9 tr\u1eebu t\u01b0\u1ee3ng": 19
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "PhobertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a7d6ffae0b68c4102f991c4d5667986167ee8da0f15911b99f8c04d1f75587a
+size 1472588812