Token Classification
Transformers
Safetensors
English
Slovenian
menthos
modernbert
log-parsing
ner
cybersecurity
Instructions to use LHRS-UM-FERI/MENTHOS-logparse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LHRS-UM-FERI/MENTHOS-logparse with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="LHRS-UM-FERI/MENTHOS-logparse")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("LHRS-UM-FERI/MENTHOS-logparse", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload 9 files
Browse files- MENTHOS-LogParsing-256/config.json +127 -0
- MENTHOS-LogParsing-256/label_to_id.json +25 -0
- MENTHOS-LogParsing-256/model.safetensors +3 -0
- MENTHOS-LogParsing-256/model_id_to_label.json +25 -0
- MENTHOS-LogParsing-256/tokenizer.json +0 -0
- MENTHOS-LogParsing-256/tokenizer_config.json +16 -0
- latency_percentiles_log-parsing.png +0 -0
- log-parsing_f1_menthos_vs_morpheus.png +0 -0
- log-parsing_menthos_throughput_samples_per_sec.png +0 -0
MENTHOS-LogParsing-256/config.json
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertForTokenClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 50281,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "mean",
|
| 12 |
+
"cls_token_id": 50281,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"dtype": "float32",
|
| 16 |
+
"embedding_dropout": 0.0,
|
| 17 |
+
"eos_token_id": 50282,
|
| 18 |
+
"global_attn_every_n_layers": 3,
|
| 19 |
+
"gradient_checkpointing": false,
|
| 20 |
+
"hidden_activation": "gelu",
|
| 21 |
+
"hidden_size": 768,
|
| 22 |
+
"id2label": {
|
| 23 |
+
"0": "[PAD]",
|
| 24 |
+
"1": "I-time_received",
|
| 25 |
+
"2": "O",
|
| 26 |
+
"3": "B-request_url",
|
| 27 |
+
"4": "B-response_bytes_clf",
|
| 28 |
+
"5": "B-request_header_referer",
|
| 29 |
+
"6": "B-request_header_user_agent__os__version_string",
|
| 30 |
+
"7": "I-request_header_user_agent",
|
| 31 |
+
"8": "I-request_header_referer",
|
| 32 |
+
"9": "B-status",
|
| 33 |
+
"10": "B-error_level",
|
| 34 |
+
"11": "I-request_http_ver",
|
| 35 |
+
"12": "B-request_http_ver",
|
| 36 |
+
"13": "I-request_url",
|
| 37 |
+
"14": "B-request_method",
|
| 38 |
+
"15": "B-remote_host",
|
| 39 |
+
"16": "I-error_level",
|
| 40 |
+
"17": "B-error_message",
|
| 41 |
+
"18": "I-error_message",
|
| 42 |
+
"19": "I-remote_host",
|
| 43 |
+
"20": "B-request_header_user_agent",
|
| 44 |
+
"21": "B-time_received",
|
| 45 |
+
"22": "UNUSED"
|
| 46 |
+
},
|
| 47 |
+
"initializer_cutoff_factor": 2.0,
|
| 48 |
+
"initializer_range": 0.02,
|
| 49 |
+
"intermediate_size": 1152,
|
| 50 |
+
"label2id": {
|
| 51 |
+
"B-error_level": 10,
|
| 52 |
+
"B-error_message": 17,
|
| 53 |
+
"B-remote_host": 15,
|
| 54 |
+
"B-request_header_referer": 5,
|
| 55 |
+
"B-request_header_user_agent": 20,
|
| 56 |
+
"B-request_header_user_agent__os__version_string": 6,
|
| 57 |
+
"B-request_http_ver": 12,
|
| 58 |
+
"B-request_method": 14,
|
| 59 |
+
"B-request_url": 3,
|
| 60 |
+
"B-response_bytes_clf": 4,
|
| 61 |
+
"B-status": 9,
|
| 62 |
+
"B-time_received": 21,
|
| 63 |
+
"I-error_level": 16,
|
| 64 |
+
"I-error_message": 18,
|
| 65 |
+
"I-remote_host": 19,
|
| 66 |
+
"I-request_header_referer": 8,
|
| 67 |
+
"I-request_header_user_agent": 7,
|
| 68 |
+
"I-request_http_ver": 11,
|
| 69 |
+
"I-request_url": 13,
|
| 70 |
+
"I-time_received": 1,
|
| 71 |
+
"O": 2,
|
| 72 |
+
"UNUSED": 22,
|
| 73 |
+
"[PAD]": 0
|
| 74 |
+
},
|
| 75 |
+
"layer_norm_eps": 1e-05,
|
| 76 |
+
"layer_types": [
|
| 77 |
+
"full_attention",
|
| 78 |
+
"sliding_attention",
|
| 79 |
+
"sliding_attention",
|
| 80 |
+
"full_attention",
|
| 81 |
+
"sliding_attention",
|
| 82 |
+
"sliding_attention",
|
| 83 |
+
"full_attention",
|
| 84 |
+
"sliding_attention",
|
| 85 |
+
"sliding_attention",
|
| 86 |
+
"full_attention",
|
| 87 |
+
"sliding_attention",
|
| 88 |
+
"sliding_attention",
|
| 89 |
+
"full_attention",
|
| 90 |
+
"sliding_attention",
|
| 91 |
+
"sliding_attention",
|
| 92 |
+
"full_attention",
|
| 93 |
+
"sliding_attention",
|
| 94 |
+
"sliding_attention",
|
| 95 |
+
"full_attention",
|
| 96 |
+
"sliding_attention",
|
| 97 |
+
"sliding_attention",
|
| 98 |
+
"full_attention"
|
| 99 |
+
],
|
| 100 |
+
"local_attention": 128,
|
| 101 |
+
"max_position_embeddings": 8192,
|
| 102 |
+
"mlp_bias": false,
|
| 103 |
+
"mlp_dropout": 0.0,
|
| 104 |
+
"model_type": "modernbert",
|
| 105 |
+
"norm_bias": false,
|
| 106 |
+
"norm_eps": 1e-05,
|
| 107 |
+
"num_attention_heads": 12,
|
| 108 |
+
"num_hidden_layers": 22,
|
| 109 |
+
"pad_token_id": 50283,
|
| 110 |
+
"position_embedding_type": "absolute",
|
| 111 |
+
"rope_parameters": {
|
| 112 |
+
"full_attention": {
|
| 113 |
+
"rope_theta": 160000.0,
|
| 114 |
+
"rope_type": "default"
|
| 115 |
+
},
|
| 116 |
+
"sliding_attention": {
|
| 117 |
+
"rope_theta": 10000.0,
|
| 118 |
+
"rope_type": "default"
|
| 119 |
+
}
|
| 120 |
+
},
|
| 121 |
+
"sep_token_id": 50282,
|
| 122 |
+
"sparse_pred_ignore_index": -100,
|
| 123 |
+
"sparse_prediction": false,
|
| 124 |
+
"tie_word_embeddings": true,
|
| 125 |
+
"transformers_version": "5.3.0",
|
| 126 |
+
"vocab_size": 50368
|
| 127 |
+
}
|
MENTHOS-LogParsing-256/label_to_id.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"X": -100,
|
| 3 |
+
"[PAD]": 0,
|
| 4 |
+
"I-time_received": 1,
|
| 5 |
+
"O": 2,
|
| 6 |
+
"B-request_url": 3,
|
| 7 |
+
"B-response_bytes_clf": 4,
|
| 8 |
+
"B-request_header_referer": 5,
|
| 9 |
+
"B-request_header_user_agent__os__version_string": 6,
|
| 10 |
+
"I-request_header_user_agent": 7,
|
| 11 |
+
"I-request_header_referer": 8,
|
| 12 |
+
"B-status": 9,
|
| 13 |
+
"B-error_level": 10,
|
| 14 |
+
"I-request_http_ver": 11,
|
| 15 |
+
"B-request_http_ver": 12,
|
| 16 |
+
"I-request_url": 13,
|
| 17 |
+
"B-request_method": 14,
|
| 18 |
+
"B-remote_host": 15,
|
| 19 |
+
"I-error_level": 16,
|
| 20 |
+
"B-error_message": 17,
|
| 21 |
+
"I-error_message": 18,
|
| 22 |
+
"I-remote_host": 19,
|
| 23 |
+
"B-request_header_user_agent": 20,
|
| 24 |
+
"B-time_received": 21
|
| 25 |
+
}
|
MENTHOS-LogParsing-256/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:422b5a0d364c7862605c36157c412774d94fcdb1a1d30eb0085ece6380aa1c43
|
| 3 |
+
size 598504388
|
MENTHOS-LogParsing-256/model_id_to_label.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"0": "[PAD]",
|
| 3 |
+
"1": "I-time_received",
|
| 4 |
+
"2": "O",
|
| 5 |
+
"3": "B-request_url",
|
| 6 |
+
"4": "B-response_bytes_clf",
|
| 7 |
+
"5": "B-request_header_referer",
|
| 8 |
+
"6": "B-request_header_user_agent__os__version_string",
|
| 9 |
+
"7": "I-request_header_user_agent",
|
| 10 |
+
"8": "I-request_header_referer",
|
| 11 |
+
"9": "B-status",
|
| 12 |
+
"10": "B-error_level",
|
| 13 |
+
"11": "I-request_http_ver",
|
| 14 |
+
"12": "B-request_http_ver",
|
| 15 |
+
"13": "I-request_url",
|
| 16 |
+
"14": "B-request_method",
|
| 17 |
+
"15": "B-remote_host",
|
| 18 |
+
"16": "I-error_level",
|
| 19 |
+
"17": "B-error_message",
|
| 20 |
+
"18": "I-error_message",
|
| 21 |
+
"19": "I-remote_host",
|
| 22 |
+
"20": "B-request_header_user_agent",
|
| 23 |
+
"21": "B-time_received",
|
| 24 |
+
"22": "UNUSED"
|
| 25 |
+
}
|
MENTHOS-LogParsing-256/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
MENTHOS-LogParsing-256/tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"is_local": false,
|
| 6 |
+
"mask_token": "[MASK]",
|
| 7 |
+
"model_input_names": [
|
| 8 |
+
"input_ids",
|
| 9 |
+
"attention_mask"
|
| 10 |
+
],
|
| 11 |
+
"model_max_length": 8192,
|
| 12 |
+
"pad_token": "[PAD]",
|
| 13 |
+
"sep_token": "[SEP]",
|
| 14 |
+
"tokenizer_class": "TokenizersBackend",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|
latency_percentiles_log-parsing.png
ADDED
|
log-parsing_f1_menthos_vs_morpheus.png
ADDED
|
log-parsing_menthos_throughput_samples_per_sec.png
ADDED
|