Upload folder using huggingface_hub

README.md

@@ -0,0 +1,98 @@
+---
+language:
+- en
+license: mit
+tags:
+- text-generation
+- lyrics
+- music
+- gpt2
+- fine-tuned
+datasets:
+- custom
+widget:
+- text: "Write lyrics for a pop song about summer love"
+---
+
+# 🎵 AI Lyrics Generator
+
+This model generates song lyrics based on prompts. It's a fine-tuned version of GPT-2 trained on a diverse dataset of song lyrics.
+
+## Model Description
+
+- **Base Model:** GPT-2
+- **Task:** Lyrics Generation
+- **Training Data:** Custom dataset of 10,000+ songs from various genres
+- **Languages:** English
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# Load model
+tokenizer = AutoTokenizer.from_pretrained("bcash2233/lyrics-generator-gpt2")
+model = AutoModelForCausalLM.from_pretrained("bcash2233/lyrics-generator-gpt2")
+
+# Generate lyrics
+prompt = "Write lyrics for a rock song about freedom"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(
+    inputs.input_ids,
+    max_length=300,
+    temperature=0.8,
+    top_p=0.9,
+    do_sample=True
+)
+
+lyrics = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(lyrics)
+```
+
+## Streamlit Demo
+
+Try the interactive web app:
+```bash
+streamlit run app.py
+```
+
+## Training Details
+
+- **Epochs:** 3
+- **Batch Size:** 4
+- **Learning Rate:** 5e-5
+- **Training Time:** ~2 hours (GPU)
+
+## Example Outputs
+
+**Prompt:** "Write lyrics for a sad ballad about heartbreak"
+
+**Output:**
+```
+I'm standing in the rain again
+Thinking 'bout the way we were
+Every memory cuts like glass
+And I can't seem to let you go...
+```
+
+## Limitations
+
+- May generate repetitive phrases
+- Best with clear, specific prompts
+- Quality varies by prompt complexity
+
+## Citation
+
+```
+@misc{lyrics-generator-gpt2,
+  author = {Your Name},
+  title = {AI Lyrics Generator},
+  year = {2024},
+  publisher = {Hugging Face},
+  url = {https://huggingface.co/bcash2233/lyrics-generator-gpt2}
+}
+```
+
+## License
+
+MIT License

config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "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
+    }
+  },
+  "transformers_version": "4.57.3",
+  "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": "4.57.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6809c7f3ce6539ad9188f9793575ddc0c72687822dd7e8c932c476d182be7dd0
+size 497774208

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,25 @@
+{
+  "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|>",
+  "extra_special_tokens": {},
+  "max_length": 512,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}