Initial upload: rpchat multi-task DistilBERT classifier

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model.onnx.data filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,23 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertMultiTask"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.57.6",
+  "vocab_size": 30522
+}

label_map_da.json

@@ -0,0 +1,23 @@
+{
+  "0": "accusation",
+  "1": "acknowledgment",
+  "2": "action",
+  "3": "agree",
+  "4": "command",
+  "5": "conditional",
+  "6": "confession",
+  "7": "disagree",
+  "8": "emote",
+  "9": "farewell",
+  "10": "flirt",
+  "11": "greeting",
+  "12": "hedge",
+  "13": "hostile",
+  "14": "intent",
+  "15": "offer",
+  "16": "opinion",
+  "17": "out_of_character",
+  "18": "question",
+  "19": "statement",
+  "20": "yes_no_question"
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c9eea385de010faa782927bce7cbea04048ddac883e15dd76979579196d7d8b
+size 268022997

model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f33cf71f1822b2c62b444b752dfab17eb7aae4d56207a2479680d969dd803356
+size 267958272

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a833e297fc68e0161855a3f3c16dff3b3b4747aa048d1a11f06c8fff154cf0
+size 267897340

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.json

@@ -0,0 +1,42 @@
+{
+  "epochs": 5,
+  "batch_size": 32,
+  "learning_rate": 3e-05,
+  "max_length": 64,
+  "lambda_manip": 0.3,
+  "num_da_labels": 21,
+  "da_label_names": [
+    "accusation",
+    "acknowledgment",
+    "action",
+    "agree",
+    "command",
+    "conditional",
+    "confession",
+    "disagree",
+    "emote",
+    "farewell",
+    "flirt",
+    "greeting",
+    "hedge",
+    "hostile",
+    "intent",
+    "offer",
+    "opinion",
+    "out_of_character",
+    "question",
+    "statement",
+    "yes_no_question"
+  ],
+  "da_train_size": 9765,
+  "manip_train_size": 12949,
+  "training_time_seconds": 64.3231897354126,
+  "da_accuracy": 0.884,
+  "da_correct": 960,
+  "da_total": 1086,
+  "manip_accuracy": 0.9875,
+  "manip_correct": 1421,
+  "manip_total": 1439,
+  "manip_fp": 8,
+  "manip_fn": 10
+}