feat: add model and tokenizer and sample config

This commit is contained in:
2024-06-21 15:02:04 +03:00
parent ee1362a605
commit 4e44b56fbb
8 changed files with 61349 additions and 0 deletions
+16
View File
@@ -0,0 +1,16 @@
{
"storage": {
"database": "log_analysis",
"user": "postgres",
"password": "postgres",
"host": "127.0.0.1",
"port": 5432
},
"vectorization_model": "/home/cloudadmin/log_analysis/services/log_analyzer/model-all-MiniLM-L6-v2",
"kafka_server": "172.17.1.45:9092",
"topic": "test_voloh",
"tokenizer": "/home/cloudadmin/log_analysis/services/log_analyzer/tokenizer-all-MiniLM-L6-v2",
"model": "/home/cloudadmin/log_analysis/services/log_analyzer/model.pkl"
}
@@ -0,0 +1,26 @@
{
"_name_or_path": "model-all-MiniLM-L6-v2",
"architectures": [
"BertModel"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 384,
"initializer_range": 0.02,
"intermediate_size": 1536,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 6,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.35.2",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 30522
}
Binary file not shown.
@@ -0,0 +1,37 @@
{
"cls_token": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"mask_token": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"sep_token": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,64 @@
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"101": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"102": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"103": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"max_length": 128,
"model_max_length": 512,
"never_split": null,
"pad_to_multiple_of": null,
"pad_token": "[PAD]",
"pad_token_type_id": 0,
"padding_side": "right",
"sep_token": "[SEP]",
"stride": 0,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]"
}
File diff suppressed because it is too large Load Diff