Upload folder using huggingface_hub

README.md

@@ -0,0 +1,34 @@
+
+# DeBERTa-v3 Log Entity Recognition Model
+
+Fine-tuned DeBERTa-v3-small for Named Entity Recognition on system and cloud logs.
+
+## Model Details
+- **Base Model**: microsoft/deberta-v3-base
+- **Training Data**: 7003 synthetic + real logs
+- **Validation F1**: Check evaluation_results.txt
+
+## Entities
+['O', 'B-SERVICE', 'I-SERVICE', 'B-ERROR', 'I-ERROR', 'B-HOST', 'I-HOST', 'B-PROCESS', 'I-PROCESS']
+
+## Usage
+```python
+from transformers import AutoTokenizer, AutoModelForTokenClassification
+from peft import PeftModel
+
+model_id = "YOUR_USERNAME/log-ner-deberta-lora"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+base_model = AutoModelForTokenClassification.from_pretrained("microsoft/deberta-v3-base")
+model = PeftModel.from_pretrained(base_model, model_id)
+
+# Extract entities
+text = "nginx timeout on server1"
+inputs = tokenizer(text, return_tensors="pt")
+outputs = model(**inputs)
+```
+
+## Training Configuration
+- LoRA rank: 32
+- Training epochs: 15
+- Learning rate: 0.0003

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.15,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "key_proj",
+    "dense",
+    "query_proj",
+    "value_proj"
+  ],
+  "task_type": "TOKEN_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73265ba4a6aab345fc3af49390da82f9b41b1771bb9f3c717f2fd2fc0277d4cc
+size 21282604

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

id2label.json

@@ -0,0 +1 @@
+{"0": "O", "1": "B-SERVICE", "2": "I-SERVICE", "3": "B-ERROR", "4": "I-ERROR", "5": "B-HOST", "6": "I-HOST", "7": "B-PROCESS", "8": "I-PROCESS"}

label2id.json

@@ -0,0 +1 @@
+{"O": 0, "B-SERVICE": 1, "I-SERVICE": 2, "B-ERROR": 3, "I-ERROR": 4, "B-HOST": 5, "I-HOST": 6, "B-PROCESS": 7, "I-PROCESS": 8}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}