初始化项目，由ModelHub XC社区提供模型

Model: smgriffin/pop-lyrics-generator-v1
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,179 @@
+---
+library_name: transformers
+tags:
+- lyrics
+- text
+- text-to-lyrics
+- artist-to-lyrics
+- text-generation
+datasets:
+- smgriffin/modern-pop-lyrics
+language:
+- en
+base_model:
+- openai-community/gpt2
+pipeline_tag: text-generation
+---
+
+# Model Card for pop-lyrics-generator-v1
+
+<!-- Provide a quick summary of what the model is/does. -->
+Finetuned from openai-community/gpt2 on smgriffin/modern-pop-lyrics - generates lyrics for specific pop artists. 
+
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+It's pretty good at generating a song structure and stylized lyrics by artist, but bad at rhyming. Sometimes repeats the same thing over and over, but so do pop artists.
+It might be good for inspiration while writing lyrics. Some of the content generated can be really silly and potentially offensive - especially if you input Lil Wayne.
+
+- **Developed by:** Scott Griffin
+- **Model type:** Generative Language
+- **Language(s) (NLP):** English, Spanish
+- **Finetuned from model [optional]:** openai-community/gpt2
+
+Check out the w&b run here: [https://wandb.ai/scottgriffinm-scott-griffin-industrial-complex/pop-lyrics-generator-v1?nw=nwuserscottgriffinm](https://wandb.ai/scottgriffinm-scott-griffin-industrial-complex/pop-lyrics-generator-v1?nw=nwuserscottgriffinm)
+
+& my blog post on making it here: [https://scottsblog.glitch.me#pop-lyrics-generator-v1](https://scottsblog.glitch.me#pop-lyrics-generator-v1)
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+This model is not for commercial use. The content is the property of the individual artist from which the model was finetuned.
+This is for research purposes only.
+
+## How to Use
+
+Use the code below to generate lyrics:
+
+```python
+from transformers import GPT2LMHeadModel, GPT2Tokenizer, pipeline
+
+# load model
+model_name = "smgriffin/pop-lyrics-generator-v1"
+model = GPT2LMHeadModel.from_pretrained(model_name)
+tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+
+# create text generation pipeline
+text_generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+# prompt for justin bieber lyrics
+artist_name = "Justin Bieber"
+prompt = f"Artist: {artist_name}\nLyrics:"
+
+# generate and print
+generated_texts = text_generator(
+    prompt, 
+    max_length=150,
+    num_return_sequences=1,  
+    temperature=0.9,  # less than .9 results in a lot of repeated lyrics
+    top_k=50,
+    top_p=0.95,
+    do_sample=True, 
+)
+
+print("Generated Lyrics:")
+print(generated_texts[0]["generated_text"])
+```
+
+
+## How to Fine-Tune Your Own Lyric Generation Model
+
+Use the code below to get finetune your own GPT2 model (for example on the smgriffin/modern-pop-lyrics dataset):
+
+```python
+import os
+import pandas as pd
+from datasets import load_dataset
+from transformers import GPT2Tokenizer, GPT2LMHeadModel, Trainer, TrainingArguments, DataCollatorForLanguageModeling
+
+
+# output directory
+output_dir = "/your/output/directory"
+os.makedirs(output_dir, exist_ok=True)
+
+# load dataset
+dataset = load_dataset("smgriffin/modern-pop-lyrics")
+
+# preprocess dataset
+def preprocess_function(example):
+    # Combine artist name with lyrics for conditioning
+    combined = [f"Artist: {artist}\nLyrics: {lyrics}\n\n" for artist, lyrics in zip(example['artist'], example['lyrics'])]
+    return {"text": combined}
+
+processed_dataset = dataset.map(preprocess_function, batched=True)
+
+# split to train and test sets
+train_test_split = processed_dataset["train"].train_test_split(test_size=0.1, seed=42)
+train_dataset = train_test_split["train"]
+val_dataset = train_test_split["test"]
+
+# load tokenizer, model
+model_name = "gpt2"  # Base GPT-2 model for fine-tuning
+tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+
+# fill pad_token with eos_tone (gpt2 doesn't have a padding token)
+tokenizer.pad_token = tokenizer.eos_token
+
+# tokenize dataset
+def tokenize_function(example):
+    tokenized = tokenizer(
+        example["text"],
+        truncation=True,
+        padding="max_length",
+        max_length=512,
+    )
+    return {
+        "input_ids": tokenized["input_ids"],
+        "attention_mask": tokenized["attention_mask"],
+        "labels": tokenized["input_ids"], 
+    }
+
+train_dataset = train_dataset.map(tokenize_function, batched=True, remove_columns=["artist", "lyrics", "text"])
+val_dataset = val_dataset.map(tokenize_function, batched=True, remove_columns=["artist", "lyrics", "text"])
+
+# data collator
+data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)
+
+# load GPT-2
+model = GPT2LMHeadModel.from_pretrained(model_name)
+
+# training arguments
+training_args = TrainingArguments(
+    output_dir=output_dir, 
+    overwrite_output_dir=True,
+    evaluation_strategy="epoch",
+    learning_rate=2e-5,
+    weight_decay=0.01,
+    per_device_train_batch_size=8, 
+    per_device_eval_batch_size=8,
+    num_train_epochs=10,  
+    save_steps=1000,
+    save_total_limit=1,  
+    logging_dir=f"{output_dir}/logs", 
+    logging_steps=50,
+    gradient_accumulation_steps=2,  
+    fp16=True, 
+    max_grad_norm=1.0,
+    push_to_hub=False,
+)
+
+# init trainer
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=train_dataset,
+    eval_dataset=val_dataset,
+    tokenizer=tokenizer,
+    data_collator=data_collator,
+)
+
+# start fine-tuning
+trainer.train()
+
+# save model
+trainer.save_model(output_dir)
+tokenizer.save_pretrained(output_dir)
+
+```

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/new_new_checkpoints/checkpoint-34000",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f18ca8e26ee8ec3a023a759dce60fdd392beb54b2a3b5134ce5ebce822ede509
+size 497774208

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}