Upload folder using huggingface_hub

README.md

@@ -0,0 +1,82 @@
+---
+language: ja
+tags:
+- modernbert
+- japanese
+- emergency-call
+- phase-detection
+- boundary-detection
+license: apache-2.0
+datasets:
+- custom
+metrics:
+- accuracy
+- f1
+---
+
+# NEC-119 ModernBERT Phase & Boundary Detector
+
+## Model Description
+
+This model is fine-tuned from `sbintuitions/modernbert-ja-310m` for Japanese emergency call (119) transcript analysis.
+It performs two tasks simultaneously:
+1. **Phase Classification**: Classifies conversation phases (INIT/LOC/INC/SUP)
+2. **Boundary Detection**: Detects phase boundaries in conversation
+
+## Training Details
+
+- **Base Model**: sbintuitions/modernbert-ja-310m
+- **Training Data**: 45,483 instances from Japanese emergency call transcripts
+- **Validation Data**: 4,984 instances
+- **Test Data**: 9,605 instances
+- **Training Configuration**:
+  - Epochs: 5
+  - Batch Size: 16 (effective 32 with gradient accumulation)
+  - Learning Rate: 1e-5
+  - Max Sequence Length: 1024 tokens
+  - Optimizer: AdamW
+  - Scheduler: Cosine
+
+## Performance
+
+### Test Set Results (After 1 epoch)
+- **Phase Classification Accuracy**: 84.9%
+- **Boundary Detection Accuracy**: 94.6%
+- **Phase F1-Macro**: 0.813
+- **Boundary F1**: 0.626
+- **Both Correct Accuracy**: 81.8%
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("your-username/nec119-modernbert-phase-boundary")
+model = AutoModel.from_pretrained("your-username/nec119-modernbert-phase-boundary")
+
+# Prepare input
+context = "previous conversation text"
+current_utterance = "current line to classify"
+inputs = tokenizer(context, current_utterance, return_tensors="pt", max_length=1024, truncation=True)
+
+# Get predictions
+with torch.no_grad():
+    outputs = model(**inputs)
+    # Extract predictions from outputs
+```
+
+## Phase Labels
+- **INIT (0)**: Initial phase
+- **LOC (1)**: Location identification phase
+- **INC (2)**: Incident details phase
+- **SUP (3)**: Support/supplementary phase
+
+## Limitations
+
+This model is specifically trained for Japanese emergency call transcripts and may not generalize well to other domains or conversation types.
+
+## License
+
+Apache 2.0

config.json

@@ -0,0 +1,45 @@
+{
+  "architectures": [
+    "ModernBertTwoHead"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "cls",
+  "cls_token_id": 6,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "float32",
+  "embedding_dropout": 0.0,
+  "eos_token_id": 2,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 25,
+  "pad_token_id": 3,
+  "position_embedding_type": "rope",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 4,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "transformers_version": "4.56.2",
+  "vocab_size": 102400
+}

label_maps.json

@@ -0,0 +1,8 @@
+{
+  "PHASE2ID": {
+    "INIT": 0,
+    "LOC": 1,
+    "INC": 2,
+    "SUP": 3
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f49f667f08b424bfce396fa1e45998621f08c761c4978265b6f16e2b58a18d6c
+size 1258483344

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<cls>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "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
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008293028e1a9d9a1038d9b63d989a2319797dfeaa03f171093a57b33a3a8277
+size 1831879

tokenizer_config.json

@@ -0,0 +1,171 @@
+{
+  "add_bos_token": true,
+  "add_dummy_prefix_space": false,
+  "add_eos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<|available_tools|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<|tool_calls|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<|tool_results|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<|code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<|file|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102397": {
+      "content": "<|prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102398": {
+      "content": "<|suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102399": {
+      "content": "<|middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<cls>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "extra_special_tokens": {},
+  "keep_accents": true,
+  "legacy": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sep_token": "<sep>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}