shawhin's picture
Upload DistilBertForSequenceClassification
9ed07d4 verified
{
"_name_or_path": "shawhin/bert-phishing-classifier_student",
"activation": "gelu",
"architectures": [
"DistilBertForSequenceClassification"
],
"attention_dropout": 0.1,
"dim": 768,
"dropout": 0.1,
"hidden_dim": 3072,
"initializer_range": 0.02,
"max_position_embeddings": 512,
"model_type": "distilbert",
"n_heads": 8,
"n_layers": 4,
"pad_token_id": 0,
"qa_dropout": 0.1,
"quantization_config": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_storage": "uint8",
"bnb_4bit_quant_type": "nf4",
"bnb_4bit_use_double_quant": true,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": null,
"llm_int8_threshold": 6.0,
"load_in_4bit": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"seq_classif_dropout": 0.2,
"sinusoidal_pos_embds": false,
"torch_dtype": "float16",
"transformers_version": "4.45.0.dev0",
"vocab_size": 30522
}