Uploads QCPG for korean dataset trained on t5-base

added_tokens.json

@@ -0,0 +1 @@
+{"COND_SYNTACTIC_DIV_20": 32134, "COND_SEMANTIC_SIM_50": 32121, "COND_SEMANTIC_SIM_70": 32125, "COND_SYNTACTIC_DIV_5": 32140, "COND_LEXICAL_DIV_30": 32105, "COND_SEMANTIC_SIM_60": 32123, "COND_SEMANTIC_SIM_55": 32122, "COND_SYNTACTIC_DIV_45": 32139, "COND_SEMANTIC_SIM_95": 32130, "COND_SYNTACTIC_DIV_25": 32135, "COND_SEMANTIC_SIM_35": 32118, "COND_SEMANTIC_SIM_40": 32119, "COND_LEXICAL_DIV_20": 32103, "COND_SYNTACTIC_DIV_65": 32144, "COND_SYNTACTIC_DIV_60": 32143, "COND_SEMANTIC_SIM_25": 32116, "COND_SYNTACTIC_DIV_30": 32136, "COND_SEMANTIC_SIM_85": 32128, "COND_LEXICAL_DIV_25": 32104, "COND_SYNTACTIC_DIV_55": 32142, "COND_SYNTACTIC_DIV_70": 32145, "COND_SEMANTIC_SIM_15": 32114, "COND_LEXICAL_DIV_5": 32109, "COND_SYNTACTIC_DIV_50": 32141, "COND_LEXICAL_DIV_15": 32102, "COND_SYNTACTIC_DIV_0": 32131, "COND_SEMANTIC_SIM_75": 32126, "COND_SYNTACTIC_DIV_15": 32133, "COND_SYNTACTIC_DIV_40": 32138, "COND_LEXICAL_DIV_60": 32112, "COND_SEMANTIC_SIM_45": 32120, "COND_SYNTACTIC_DIV_35": 32137, "COND_LEXICAL_DIV_35": 32106, "COND_LEXICAL_DIV_10": 32101, "COND_SEMANTIC_SIM_20": 32115, "COND_SEMANTIC_SIM_90": 32129, "COND_SEMANTIC_SIM_65": 32124, "COND_LEXICAL_DIV_40": 32107, "COND_LEXICAL_DIV_45": 32108, "COND_SEMANTIC_SIM_10": 32113, "COND_LEXICAL_DIV_55": 32111, "COND_SEMANTIC_SIM_80": 32127, "COND_LEXICAL_DIV_0": 32100, "COND_SYNTACTIC_DIV_10": 32132, "COND_LEXICAL_DIV_50": 32110, "COND_SEMANTIC_SIM_30": 32117}

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "transformers_version": "4.6.1",
+  "use_cache": true,
+  "vocab_size": 32146
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a60a6253b24081ae9d440d4d9b6aa3dec27a40dedea9f5abb34860c4d64b4dee
+size 891788305

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["COND_LEXICAL_DIV_0", "COND_LEXICAL_DIV_10", "COND_LEXICAL_DIV_15", "COND_LEXICAL_DIV_20", "COND_LEXICAL_DIV_25", "COND_LEXICAL_DIV_30", "COND_LEXICAL_DIV_35", "COND_LEXICAL_DIV_40", "COND_LEXICAL_DIV_45", "COND_LEXICAL_DIV_5", "COND_LEXICAL_DIV_50", "COND_LEXICAL_DIV_55", "COND_LEXICAL_DIV_60", "COND_SEMANTIC_SIM_10", "COND_SEMANTIC_SIM_15", "COND_SEMANTIC_SIM_20", "COND_SEMANTIC_SIM_25", "COND_SEMANTIC_SIM_30", "COND_SEMANTIC_SIM_35", "COND_SEMANTIC_SIM_40", "COND_SEMANTIC_SIM_45", "COND_SEMANTIC_SIM_50", "COND_SEMANTIC_SIM_55", "COND_SEMANTIC_SIM_60", "COND_SEMANTIC_SIM_65", "COND_SEMANTIC_SIM_70", "COND_SEMANTIC_SIM_75", "COND_SEMANTIC_SIM_80", "COND_SEMANTIC_SIM_85", "COND_SEMANTIC_SIM_90", "COND_SEMANTIC_SIM_95", "COND_SYNTACTIC_DIV_0", "COND_SYNTACTIC_DIV_10", "COND_SYNTACTIC_DIV_15", "COND_SYNTACTIC_DIV_20", "COND_SYNTACTIC_DIV_25", "COND_SYNTACTIC_DIV_30", "COND_SYNTACTIC_DIV_35", "COND_SYNTACTIC_DIV_40", "COND_SYNTACTIC_DIV_45", "COND_SYNTACTIC_DIV_5", "COND_SYNTACTIC_DIV_50", "COND_SYNTACTIC_DIV_55", "COND_SYNTACTIC_DIV_60", "COND_SYNTACTIC_DIV_65", "COND_SYNTACTIC_DIV_70"]}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": ["COND_LEXICAL_DIV_0", "COND_LEXICAL_DIV_10", "COND_LEXICAL_DIV_15", "COND_LEXICAL_DIV_20", "COND_LEXICAL_DIV_25", "COND_LEXICAL_DIV_30", "COND_LEXICAL_DIV_35", "COND_LEXICAL_DIV_40", "COND_LEXICAL_DIV_45", "COND_LEXICAL_DIV_5", "COND_LEXICAL_DIV_50", "COND_LEXICAL_DIV_55", "COND_LEXICAL_DIV_60", "COND_SEMANTIC_SIM_10", "COND_SEMANTIC_SIM_15", "COND_SEMANTIC_SIM_20", "COND_SEMANTIC_SIM_25", "COND_SEMANTIC_SIM_30", "COND_SEMANTIC_SIM_35", "COND_SEMANTIC_SIM_40", "COND_SEMANTIC_SIM_45", "COND_SEMANTIC_SIM_50", "COND_SEMANTIC_SIM_55", "COND_SEMANTIC_SIM_60", "COND_SEMANTIC_SIM_65", "COND_SEMANTIC_SIM_70", "COND_SEMANTIC_SIM_75", "COND_SEMANTIC_SIM_80", "COND_SEMANTIC_SIM_85", "COND_SEMANTIC_SIM_90", "COND_SEMANTIC_SIM_95", "COND_SYNTACTIC_DIV_0", "COND_SYNTACTIC_DIV_10", "COND_SYNTACTIC_DIV_15", "COND_SYNTACTIC_DIV_20", "COND_SYNTACTIC_DIV_25", "COND_SYNTACTIC_DIV_30", "COND_SYNTACTIC_DIV_35", "COND_SYNTACTIC_DIV_40", "COND_SYNTACTIC_DIV_45", "COND_SYNTACTIC_DIV_5", "COND_SYNTACTIC_DIV_50", "COND_SYNTACTIC_DIV_55", "COND_SYNTACTIC_DIV_60", "COND_SYNTACTIC_DIV_65", "COND_SYNTACTIC_DIV_70"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-base"}