init

README.md

@@ -0,0 +1,25 @@
+---
+language: "id"
+license: "mit"
+datasets:
+- Squad 
+- XQuad
+- Tydiqa
+widget:
+- text: "I love you"
+---
+
+## Prefix use
+Use prefix "question: {question} context: {context}" before input to generate the translation
+e.g
+"question: siapa nama saya ? context: nama saya andi. saya tinggal di jakarta. istri saya bernama raisa"
+
+for generate question prefix
+
+generate questions: nama saya andi. saya tinggal di jakarta. istri saya bernama raisa
+
+## Training data
+
+Squad 
+XQuad 
+Tydiqa

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/home/patrick/hugging_face/t5/mt5-large",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "transformers_version": "4.3.0.dev0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6843490776cc991e3ae6cd4bec28a88920235e602efecc747dde4fb5e9862a22
+size 4918583567

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "tokenizer_file": null, "name_or_path": "google/mt5-small"}