Add files using upload-large-folder tool

README.md

@@ -0,0 +1,100 @@
+---
+language:
+- vi
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-classification
+tags:
+- vietnamese
+- phobert
+- disaster-response
+- emergency-detection
+- text-classification
+- peft
+- lora
+base_model: vinai/phobert-base
+---
+
+# PhoBERT Vietnamese Cau Cuu Classifier
+
+PhoBERT-based Vietnamese Facebook comment classifier for detecting **"cầu cứu"** comments during natural-disaster situations.
+
+## Labels
+
+- `0`: `khong_cau_cuu`
+- `1`: `cau_cuu`
+
+## Intended use
+
+This model is designed to prioritize **high recall** for emergency rescue requests in Vietnamese social-media comments, especially when comments may contain distress language, location hints, phone numbers, or SOS markers.
+
+## Training setup
+
+- Base model: `vinai/phobert-base`
+- Fine-tuning method: LoRA / PEFT
+- Evaluation checkpoint source: `/content/phobert-cau-cuu/saved_model/checkpoint-171`
+- Decision threshold for deployment: `0.4941`
+- Threshold selection policy: `target_recall` with validation target recall `0.88`
+
+## Validation metrics at selected threshold
+
+- Accuracy: `0.8469`
+- F1 macro: `0.8380`
+- F1 (`cau_cuu`): `0.8000`
+- Recall (`cau_cuu`): `0.8955`
+- Precision (`cau_cuu`): `0.7229`
+
+## Test metrics
+
+- Accuracy: `0.8520`
+- F1 macro: `0.8430`
+- F1 (`cau_cuu`): `0.8054`
+- Recall (`cau_cuu`): `0.9091`
+- Precision (`cau_cuu`): `0.7229`
+
+## Confusion matrix on test set
+
+```text
+107 23
+6 60
+```
+
+## Recommended inference rule
+
+Convert logits to probabilities and classify as `cau_cuu` when:
+
+```python
+prob_cau_cuu >= 0.4941
+```
+
+This threshold was chosen on the validation set to preserve strong recall while improving `F1(cau_cuu)` and overall accuracy.
+
+## Example loading code
+
+```python
+import torch
+from peft import AutoPeftModelForSequenceClassification
+from transformers import AutoTokenizer
+
+repo_id = "dat201204/phobert-vi-caucu-classifier"
+threshold = 0.4941
+
+tokenizer = AutoTokenizer.from_pretrained(repo_id, use_fast=False)
+model = AutoPeftModelForSequenceClassification.from_pretrained(repo_id)
+model.eval()
+
+text = "Cuu voi, nha em dang ngap va co nguoi gia bi ket"
+inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=256)
+with torch.no_grad():
+    logits = model(**inputs).logits
+    prob_cau_cuu = torch.softmax(logits, dim=-1)[0, 1].item()
+
+label = "cau_cuu" if prob_cau_cuu >= threshold else "khong_cau_cuu"
+print({"label": label, "prob_cau_cuu": prob_cau_cuu})
+```
+
+## Limitations
+
+- The dataset was weakly supervised in the first labeling stage and may contain residual noise.
+- The model is optimized for disaster-response triage, not for general sentiment or topic classification.
+- Human verification is still recommended for high-stakes rescue coordination.

adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "vinai/phobert-base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "value",
+    "query"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbfeb72d109817a757e709a9ad235bb30988e3eea400ecc1e528ffe33f6ea767
+size 4735200

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": null,
+  "backend": "custom",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}