Upload TFRobertaForSequenceClassification
Browse files- README.md +47 -0
 - config.json +52 -0
 - tf_model.h5 +3 -0
 
    	
        README.md
    ADDED
    
    | 
         @@ -0,0 +1,47 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            ---
         
     | 
| 2 | 
         
            +
            tags:
         
     | 
| 3 | 
         
            +
            - generated_from_keras_callback
         
     | 
| 4 | 
         
            +
            model-index:
         
     | 
| 5 | 
         
            +
            - name: bias_identificaiton45
         
     | 
| 6 | 
         
            +
              results: []
         
     | 
| 7 | 
         
            +
            ---
         
     | 
| 8 | 
         
            +
             
     | 
| 9 | 
         
            +
            <!-- This model card has been generated automatically according to the information Keras had access to. You should
         
     | 
| 10 | 
         
            +
            probably proofread and complete it, then remove this comment. -->
         
     | 
| 11 | 
         
            +
             
     | 
| 12 | 
         
            +
            # bias_identificaiton45
         
     | 
| 13 | 
         
            +
             
     | 
| 14 | 
         
            +
            This model was trained from scratch on an unknown dataset.
         
     | 
| 15 | 
         
            +
            It achieves the following results on the evaluation set:
         
     | 
| 16 | 
         
            +
             
     | 
| 17 | 
         
            +
             
     | 
| 18 | 
         
            +
            ## Model description
         
     | 
| 19 | 
         
            +
             
     | 
| 20 | 
         
            +
            More information needed
         
     | 
| 21 | 
         
            +
             
     | 
| 22 | 
         
            +
            ## Intended uses & limitations
         
     | 
| 23 | 
         
            +
             
     | 
| 24 | 
         
            +
            More information needed
         
     | 
| 25 | 
         
            +
             
     | 
| 26 | 
         
            +
            ## Training and evaluation data
         
     | 
| 27 | 
         
            +
             
     | 
| 28 | 
         
            +
            More information needed
         
     | 
| 29 | 
         
            +
             
     | 
| 30 | 
         
            +
            ## Training procedure
         
     | 
| 31 | 
         
            +
             
     | 
| 32 | 
         
            +
            ### Training hyperparameters
         
     | 
| 33 | 
         
            +
             
     | 
| 34 | 
         
            +
            The following hyperparameters were used during training:
         
     | 
| 35 | 
         
            +
            - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 1e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
         
     | 
| 36 | 
         
            +
            - training_precision: float32
         
     | 
| 37 | 
         
            +
             
     | 
| 38 | 
         
            +
            ### Training results
         
     | 
| 39 | 
         
            +
             
     | 
| 40 | 
         
            +
             
     | 
| 41 | 
         
            +
             
     | 
| 42 | 
         
            +
            ### Framework versions
         
     | 
| 43 | 
         
            +
             
     | 
| 44 | 
         
            +
            - Transformers 4.39.3
         
     | 
| 45 | 
         
            +
            - TensorFlow 2.15.0
         
     | 
| 46 | 
         
            +
            - Datasets 2.18.0
         
     | 
| 47 | 
         
            +
            - Tokenizers 0.15.2
         
     | 
    	
        config.json
    ADDED
    
    | 
         @@ -0,0 +1,52 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment-latest",
         
     | 
| 3 | 
         
            +
              "architectures": [
         
     | 
| 4 | 
         
            +
                "RobertaForSequenceClassification"
         
     | 
| 5 | 
         
            +
              ],
         
     | 
| 6 | 
         
            +
              "attention_probs_dropout_prob": 0.1,
         
     | 
| 7 | 
         
            +
              "bos_token_id": 0,
         
     | 
| 8 | 
         
            +
              "classifier_dropout": null,
         
     | 
| 9 | 
         
            +
              "eos_token_id": 2,
         
     | 
| 10 | 
         
            +
              "gradient_checkpointing": false,
         
     | 
| 11 | 
         
            +
              "hidden_act": "gelu",
         
     | 
| 12 | 
         
            +
              "hidden_dropout_prob": 0.1,
         
     | 
| 13 | 
         
            +
              "hidden_size": 768,
         
     | 
| 14 | 
         
            +
              "id2label": {
         
     | 
| 15 | 
         
            +
                "0": "LABEL_0",
         
     | 
| 16 | 
         
            +
                "1": "LABEL_1",
         
     | 
| 17 | 
         
            +
                "2": "LABEL_2",
         
     | 
| 18 | 
         
            +
                "3": "LABEL_3",
         
     | 
| 19 | 
         
            +
                "4": "LABEL_4",
         
     | 
| 20 | 
         
            +
                "5": "LABEL_5",
         
     | 
| 21 | 
         
            +
                "6": "LABEL_6",
         
     | 
| 22 | 
         
            +
                "7": "LABEL_7",
         
     | 
| 23 | 
         
            +
                "8": "LABEL_8",
         
     | 
| 24 | 
         
            +
                "9": "LABEL_9"
         
     | 
| 25 | 
         
            +
              },
         
     | 
| 26 | 
         
            +
              "initializer_range": 0.02,
         
     | 
| 27 | 
         
            +
              "intermediate_size": 3072,
         
     | 
| 28 | 
         
            +
              "label2id": {
         
     | 
| 29 | 
         
            +
                "LABEL_0": 0,
         
     | 
| 30 | 
         
            +
                "LABEL_1": 1,
         
     | 
| 31 | 
         
            +
                "LABEL_2": 2,
         
     | 
| 32 | 
         
            +
                "LABEL_3": 3,
         
     | 
| 33 | 
         
            +
                "LABEL_4": 4,
         
     | 
| 34 | 
         
            +
                "LABEL_5": 5,
         
     | 
| 35 | 
         
            +
                "LABEL_6": 6,
         
     | 
| 36 | 
         
            +
                "LABEL_7": 7,
         
     | 
| 37 | 
         
            +
                "LABEL_8": 8,
         
     | 
| 38 | 
         
            +
                "LABEL_9": 9
         
     | 
| 39 | 
         
            +
              },
         
     | 
| 40 | 
         
            +
              "layer_norm_eps": 1e-05,
         
     | 
| 41 | 
         
            +
              "max_position_embeddings": 514,
         
     | 
| 42 | 
         
            +
              "model_type": "roberta",
         
     | 
| 43 | 
         
            +
              "num_attention_heads": 12,
         
     | 
| 44 | 
         
            +
              "num_hidden_layers": 12,
         
     | 
| 45 | 
         
            +
              "pad_token_id": 1,
         
     | 
| 46 | 
         
            +
              "position_embedding_type": "absolute",
         
     | 
| 47 | 
         
            +
              "torch_dtype": "float32",
         
     | 
| 48 | 
         
            +
              "transformers_version": "4.39.3",
         
     | 
| 49 | 
         
            +
              "type_vocab_size": 1,
         
     | 
| 50 | 
         
            +
              "use_cache": true,
         
     | 
| 51 | 
         
            +
              "vocab_size": 50265
         
     | 
| 52 | 
         
            +
            }
         
     | 
    	
        tf_model.h5
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:4432e621c12a7f025b0fb761130a1ce3b1c708681768ef6d989f26e7cddc2dd5
         
     | 
| 3 | 
         
            +
            size 498902848
         
     |