Upload config.json with huggingface_hub
Browse files- config.json +76 -0
config.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation_autoset": true,
|
| 3 |
+
"_name_or_path": "/tmp/tmpcixd161m",
|
| 4 |
+
"_num_labels": 5,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"BertForSequenceClassification"
|
| 7 |
+
],
|
| 8 |
+
"attention_probs_dropout_prob": 0.1,
|
| 9 |
+
"classifier_dropout": null,
|
| 10 |
+
"directionality": "bidi",
|
| 11 |
+
"finetuning_task": "sentiment-analysis",
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "1 star",
|
| 17 |
+
"1": "2 stars",
|
| 18 |
+
"2": "3 stars",
|
| 19 |
+
"3": "4 stars",
|
| 20 |
+
"4": "5 stars"
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 3072,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"1 star": 0,
|
| 26 |
+
"2 stars": 1,
|
| 27 |
+
"3 stars": 2,
|
| 28 |
+
"4 stars": 3,
|
| 29 |
+
"5 stars": 4
|
| 30 |
+
},
|
| 31 |
+
"layer_norm_eps": 1e-12,
|
| 32 |
+
"max_position_embeddings": 512,
|
| 33 |
+
"model_type": "bert",
|
| 34 |
+
"neuron": {
|
| 35 |
+
"auto_cast": "matmul",
|
| 36 |
+
"auto_cast_type": "bf16",
|
| 37 |
+
"compiler_type": "neuronx-cc",
|
| 38 |
+
"compiler_version": "2.16.372.0+4a9b2326",
|
| 39 |
+
"disable_fallback": false,
|
| 40 |
+
"disable_fast_relayout": false,
|
| 41 |
+
"dynamic_batch_size": false,
|
| 42 |
+
"inline_weights_to_neff": true,
|
| 43 |
+
"input_names": [
|
| 44 |
+
"input_ids",
|
| 45 |
+
"attention_mask",
|
| 46 |
+
"token_type_ids"
|
| 47 |
+
],
|
| 48 |
+
"model_type": "bert",
|
| 49 |
+
"optlevel": "2",
|
| 50 |
+
"output_attentions": false,
|
| 51 |
+
"output_hidden_states": false,
|
| 52 |
+
"output_names": [
|
| 53 |
+
"logits"
|
| 54 |
+
],
|
| 55 |
+
"static_batch_size": 1,
|
| 56 |
+
"static_sequence_length": 128,
|
| 57 |
+
"tensor_parallel_size": 1
|
| 58 |
+
},
|
| 59 |
+
"num_attention_heads": 12,
|
| 60 |
+
"num_hidden_layers": 12,
|
| 61 |
+
"output_past": true,
|
| 62 |
+
"pad_token_id": 0,
|
| 63 |
+
"pooler_fc_size": 768,
|
| 64 |
+
"pooler_num_attention_heads": 12,
|
| 65 |
+
"pooler_num_fc_layers": 3,
|
| 66 |
+
"pooler_size_per_head": 128,
|
| 67 |
+
"pooler_type": "first_token_transform",
|
| 68 |
+
"position_embedding_type": "absolute",
|
| 69 |
+
"task": "text-classification",
|
| 70 |
+
"torch_dtype": "float32",
|
| 71 |
+
"torchscript": true,
|
| 72 |
+
"transformers_version": "4.49.0",
|
| 73 |
+
"type_vocab_size": 2,
|
| 74 |
+
"use_cache": true,
|
| 75 |
+
"vocab_size": 105879
|
| 76 |
+
}
|