Upload neuronxcc-2.16.372.0+4a9b2326/MODULE_c38b69400c9a50249749/config.json with huggingface_hub
Browse files
    	
        neuronxcc-2.16.372.0+4a9b2326/MODULE_c38b69400c9a50249749/config.json
    ADDED
    
    | 
         @@ -0,0 +1,51 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "_attn_implementation_autoset": true,
         
     | 
| 3 | 
         
            +
              "_name_or_path": "bert-base-uncased",
         
     | 
| 4 | 
         
            +
              "architectures": [
         
     | 
| 5 | 
         
            +
                "BertForMaskedLM"
         
     | 
| 6 | 
         
            +
              ],
         
     | 
| 7 | 
         
            +
              "attention_probs_dropout_prob": 0.1,
         
     | 
| 8 | 
         
            +
              "classifier_dropout": null,
         
     | 
| 9 | 
         
            +
              "gradient_checkpointing": false,
         
     | 
| 10 | 
         
            +
              "hidden_act": "gelu",
         
     | 
| 11 | 
         
            +
              "hidden_dropout_prob": 0.1,
         
     | 
| 12 | 
         
            +
              "hidden_size": 768,
         
     | 
| 13 | 
         
            +
              "initializer_range": 0.02,
         
     | 
| 14 | 
         
            +
              "intermediate_size": 3072,
         
     | 
| 15 | 
         
            +
              "layer_norm_eps": 1e-12,
         
     | 
| 16 | 
         
            +
              "max_position_embeddings": 512,
         
     | 
| 17 | 
         
            +
              "model_type": "bert",
         
     | 
| 18 | 
         
            +
              "neuron": {
         
     | 
| 19 | 
         
            +
                "auto_cast": null,
         
     | 
| 20 | 
         
            +
                "auto_cast_type": null,
         
     | 
| 21 | 
         
            +
                "compiler_type": "neuronx-cc",
         
     | 
| 22 | 
         
            +
                "compiler_version": "2.16.372.0+4a9b2326",
         
     | 
| 23 | 
         
            +
                "dynamic_batch_size": false,
         
     | 
| 24 | 
         
            +
                "inline_weights_to_neff": true,
         
     | 
| 25 | 
         
            +
                "input_names": [
         
     | 
| 26 | 
         
            +
                  "input_ids",
         
     | 
| 27 | 
         
            +
                  "attention_mask",
         
     | 
| 28 | 
         
            +
                  "token_type_ids"
         
     | 
| 29 | 
         
            +
                ],
         
     | 
| 30 | 
         
            +
                "model_type": "bert",
         
     | 
| 31 | 
         
            +
                "optlevel": "2",
         
     | 
| 32 | 
         
            +
                "output_attentions": false,
         
     | 
| 33 | 
         
            +
                "output_hidden_states": false,
         
     | 
| 34 | 
         
            +
                "output_names": [
         
     | 
| 35 | 
         
            +
                  "logits"
         
     | 
| 36 | 
         
            +
                ],
         
     | 
| 37 | 
         
            +
                "static_batch_size": 1,
         
     | 
| 38 | 
         
            +
                "static_sequence_length": 128,
         
     | 
| 39 | 
         
            +
                "tensor_parallel_size": 1
         
     | 
| 40 | 
         
            +
              },
         
     | 
| 41 | 
         
            +
              "num_attention_heads": 12,
         
     | 
| 42 | 
         
            +
              "num_hidden_layers": 12,
         
     | 
| 43 | 
         
            +
              "pad_token_id": 0,
         
     | 
| 44 | 
         
            +
              "position_embedding_type": "absolute",
         
     | 
| 45 | 
         
            +
              "task": "fill-mask",
         
     | 
| 46 | 
         
            +
              "torchscript": true,
         
     | 
| 47 | 
         
            +
              "transformers_version": "4.48.3",
         
     | 
| 48 | 
         
            +
              "type_vocab_size": 2,
         
     | 
| 49 | 
         
            +
              "use_cache": true,
         
     | 
| 50 | 
         
            +
              "vocab_size": 30522
         
     | 
| 51 | 
         
            +
            }
         
     |