[I] Batman.

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,63 @@
+# Lyrics Generation with Masked Sequence-to-Sequence Pretraining
+
+This repository demostrate a format-controllable Chinese lyric generator, fine-tuned on [Chinese-Lyric-Corpus](https://github.com/gaussic/Chinese-Lyric-Corpus) using a [MASS](https://arxiv.org/abs/1905.02450)-like strategy.
+
+## Usage
+
+## Initialization.
+
+```
+from transformers import MT5ForConditionalGeneration, MT5Tokenizer, Text2TextGenerationPipeline
+model_path = "zake7749/chinese-lyrics-generation-mass"
+model = MT5ForConditionalGeneration.from_pretrained(model_path)
+tokenizer = MT5Tokenizer.from_pretrained(model_path)
+pipe = Text2TextGenerationPipeline(model=model, tokenizer=tokenizer)
+```
+
+## Generate lyrics with a template
+
+```
+template = "風花雪月。像XXXXXXXXXX。日升月落。仿若XXXXXXXXXX。"
+lyric = pipe(template, max_length=128, top_p=0.8, do_sample=True, repetition_penalty=1.2)[0]['generated_text']
+print(lyric) # 風花雪月。像你在我的夢裡慢慢散落。日升月落。仿若我宿命無法陪隨你走過
+```
+
+## Acrostic
+
+```
+template = "分XXXXXX。手XXXXXXXXX。之XXXXXXX。後XXXXXXXXX。"
+lyric = pipe(template, max_length=128, top_p=0.8, do_sample=True, repetition_penalty=1.2)[0]['generated_text']
+print(lyric) # 分開後激情浮現。手牽著手走過的那一天。之間有太多的危險。後悔一點點,傷心一片。
+```
+
+## Free-Style.
+
+```
+import random
+
+min_sentence_num, max_sentence_num = 2, 5
+min_characher_num, max_character_num = 4, 10
+
+num_sentences = random.randint(min_sentence_num,  max_sentence_num)
+num_words = ["X" * random.randint(min_characher_num, max_character_num)
+             for _ in range(num_sentences)]
+             
+template = "。".join(num_words) + "。"
+lyric = pipe(template, max_length=128, top_p=0.8, do_sample=True, repetition_penalty=1.2)[0]['generated_text']
+print(f"{template}\n{lyric}")
+
+# XXXXXXXXXX。XXXXXXXXXX。XXXXXX。XXXXXXX。XXXXXXXX。
+# 讓我為你再勇敢下一次。也許我唱的歌還可以。算是你的天使。如果我們不在一起。是否就不會有距離。
+```
+
+# Note
+
+The model is still under training, so sometimes it might not follow the template explicitly, especially for long sequences generation.
+
+# Disclaimer
+
+This lyric generator is for academic purposes only. Users of this model should exercise caution and carefully evaluate the results before using them for any commercial or non-academic purpose. We are not liable for any damages or losses resulting from the use or misuse of the model.
+
+---
+license: mit
+---

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "mt5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

.ipynb_checkpoints/special_tokens_map-checkpoint.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

.ipynb_checkpoints/tokenizer_config-checkpoint.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "name_or_path": "bigscience/mt0-base",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

README.md

@@ -1,3 +1,63 @@
+# Lyrics Generation with Masked Sequence-to-Sequence Pretraining
+
+This repository demostrate a format-controllable Chinese lyric generator, fine-tuned on [Chinese-Lyric-Corpus](https://github.com/gaussic/Chinese-Lyric-Corpus) using a [MASS](https://arxiv.org/abs/1905.02450)-like strategy.
+
+## Usage
+
+## Initialization.
+
+```
+from transformers import MT5ForConditionalGeneration, MT5Tokenizer, Text2TextGenerationPipeline
+model_path = "zake7749/chinese-lyrics-generation-mass"
+model = MT5ForConditionalGeneration.from_pretrained(model_path)
+tokenizer = MT5Tokenizer.from_pretrained(model_path)
+pipe = Text2TextGenerationPipeline(model=model, tokenizer=tokenizer)
+```
+
+## Generate lyrics with a template
+
+```
+template = "風花雪月。像XXXXXXXXXX。日升月落。仿若XXXXXXXXXX。"
+lyric = pipe(template, max_length=128, top_p=0.8, do_sample=True, repetition_penalty=1.2)[0]['generated_text']
+print(lyric) # 風花雪月。像你在我的夢裡慢慢散落。日升月落。仿若我宿命無法陪隨你走過
+```
+
+## Acrostic
+
+```
+template = "分XXXXXX。手XXXXXXXXX。之XXXXXXX。後XXXXXXXXX。"
+lyric = pipe(template, max_length=128, top_p=0.8, do_sample=True, repetition_penalty=1.2)[0]['generated_text']
+print(lyric) # 分開後激情浮現。手牽著手走過的那一天。之間有太多的危險。後悔一點點,傷心一片。
+```
+
+## Free-Style.
+
+```
+import random
+
+min_sentence_num, max_sentence_num = 2, 5
+min_characher_num, max_character_num = 4, 10
+
+num_sentences = random.randint(min_sentence_num,  max_sentence_num)
+num_words = ["X" * random.randint(min_characher_num, max_character_num)
+             for _ in range(num_sentences)]
+             
+template = "。".join(num_words) + "。"
+lyric = pipe(template, max_length=128, top_p=0.8, do_sample=True, repetition_penalty=1.2)[0]['generated_text']
+print(f"{template}\n{lyric}")
+
+# XXXXXXXXXX。XXXXXXXXXX。XXXXXX。XXXXXXX。XXXXXXXX。
+# 讓我為你再勇敢下一次。也許我唱的歌還可以。算是你的天使。如果我們不在一起。是否就不會有距離。
+```
+
+# Note
+
+The model is still under training, so sometimes it might not follow the template explicitly, especially for long sequences generation.
+
+# Disclaimer
+
+This lyric generator is for academic purposes only. Users of this model should exercise caution and carefully evaluate the results before using them for any commercial or non-academic purpose. We are not liable for any damages or losses resulting from the use or misuse of the model.
+
 ---
 license: mit
 ---

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "mt5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4853a0e8df9f4aff8392fdcf9534e924760a35e908e363b625f2ca132e3b32a4
+size 2329696205

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "name_or_path": "bigscience/mt0-base",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}