初始化项目，由ModelHub XC社区提供模型
Model: Vedant3907/gpt2-irish-folk-tune-generator Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.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
|
||||
assets/irish-gpt2-model.mp4 filter=lfs diff=lfs merge=lfs -text
|
||||
195
README.md
Normal file
195
README.md
Normal file
@@ -0,0 +1,195 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: mit
|
||||
library_name: transformers
|
||||
base_model: openai-community/gpt2
|
||||
datasets:
|
||||
- sander-wood/irishman
|
||||
tags:
|
||||
- text-generation
|
||||
- music-generation
|
||||
- abc-notation
|
||||
- irish-music
|
||||
- gpt2
|
||||
- full-finetune
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
Try the live demo Space: https://huggingface.co/spaces/Vedant3907/gpt2-irish-folk-tune-generator-space
|
||||
|
||||
|
||||
<video controls width="100%">
|
||||
<source src="https://huggingface.co/Vedant3907/gpt2-irish-folk-tune-generator/resolve/main/assets/irish-gpt2-model.mp4" type="video/mp4">
|
||||
</video>
|
||||
|
||||
Weekend project demo: an original dataset tune is played first, followed by a GPT-2 generated tune from similar ABC notation context.
|
||||
|
||||
|
||||
# GPT-2 Irish ABC Tune Generator
|
||||
|
||||
This model is a full fine-tune of `openai-community/gpt2` on the
|
||||
`sander-wood/irishman` dataset, a collection of Irish folk tunes represented in
|
||||
ABC notation.
|
||||
|
||||
The model generates symbolic music text, not audio. Generated output can be
|
||||
pasted into an ABC player such as [abc.rectanglered.com](https://abc.rectanglered.com/)
|
||||
or [ABCjs Editor](https://editor.drawthedots.com/) to hear the tune.
|
||||
|
||||
## Model Details
|
||||
|
||||
- **Base model:** `openai-community/gpt2`
|
||||
- **Training method:** Full fine-tuning
|
||||
- **Dataset:** `sander-wood/irishman`
|
||||
- **Task:** Causal language modeling / ABC notation continuation
|
||||
- **Max sequence length:** 512 tokens
|
||||
- **Training hardware:** Google Colab T4 GPU
|
||||
- **Training duration:** Approximately one epoch
|
||||
- **Validation loss:** `0.9962592720985413`
|
||||
|
||||
## What The Model Learns
|
||||
|
||||
The training text was formatted as:
|
||||
|
||||
```text
|
||||
<control code>
|
||||
<ABC notation>
|
||||
```
|
||||
|
||||
So a prompt can start with a control code, and the model will continue by
|
||||
generating ABC notation.
|
||||
|
||||
Example prompt:
|
||||
|
||||
```text
|
||||
S:2 B:8 E:6 B:8
|
||||
```
|
||||
|
||||
The output should look like ABC music notation with headers and note sequences.
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
import torch
|
||||
|
||||
model_id = "Vedant3907/gpt2-irish-folk-tune-generator"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_id)
|
||||
|
||||
device = "cuda" if torch.cuda.is_available() else "cpu"
|
||||
model.to(device)
|
||||
model.eval()
|
||||
|
||||
def generate_tune(prompt="S:2 B:8 E:6 B:8\n", max_new_tokens=400):
|
||||
inputs = tokenizer(prompt, return_tensors="pt").to(device)
|
||||
with torch.no_grad():
|
||||
output = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=max_new_tokens,
|
||||
do_sample=True,
|
||||
temperature=0.9,
|
||||
top_k=40,
|
||||
top_p=0.95,
|
||||
pad_token_id=tokenizer.eos_token_id,
|
||||
eos_token_id=tokenizer.eos_token_id,
|
||||
)
|
||||
return tokenizer.decode(output[0], skip_special_tokens=True)
|
||||
|
||||
print(generate_tune())
|
||||
```
|
||||
|
||||
## Example Prompt
|
||||
|
||||
```text
|
||||
S:2 B:8 E:6 B:8
|
||||
```
|
||||
|
||||
If the generated output does not include a complete ABC header, add one manually
|
||||
before playing it:
|
||||
|
||||
```text
|
||||
X:1
|
||||
M:4/4
|
||||
L:1/8
|
||||
K:G
|
||||
```
|
||||
|
||||
Then paste the full ABC text into:
|
||||
|
||||
- <https://abc.rectanglered.com/>
|
||||
- <https://editor.drawthedots.com/>
|
||||
- <https://thesession.org/tunes/convert>
|
||||
|
||||
## Evaluation
|
||||
|
||||
The model was evaluated on the dataset validation split.
|
||||
|
||||
```text
|
||||
eval_loss: 0.9962592720985413
|
||||
```
|
||||
|
||||
The final logged training loss was around `1.02`, and the validation loss was
|
||||
close to that value, suggesting the model did not obviously overfit during this
|
||||
run.
|
||||
|
||||
|
||||
|
||||
## Training Loss Table
|
||||
|
||||
Compact view of the training loss curve. The full logged loss table is available in `training_loss_curve.csv`.
|
||||
|
||||
| Step | Training Loss |
|
||||
|---:|---:|
|
||||
| 50 | 3.143394 |
|
||||
| 500 | 1.461160 |
|
||||
| 1000 | 1.315162 |
|
||||
| 1500 | 1.255494 |
|
||||
| 2000 | 1.233580 |
|
||||
| 2500 | 1.160884 |
|
||||
| 3000 | 1.140212 |
|
||||
| 3500 | 1.128867 |
|
||||
| 4000 | 1.115015 |
|
||||
| 4500 | 1.089873 |
|
||||
| 5000 | 1.078019 |
|
||||
| 5500 | 1.059447 |
|
||||
| 6000 | 1.082058 |
|
||||
| 6500 | 1.072979 |
|
||||
| 7000 | 1.060261 |
|
||||
| 7500 | 1.066326 |
|
||||
| 8000 | 1.051891 |
|
||||
| 8500 | 1.054574 |
|
||||
| 9000 | 1.058629 |
|
||||
| 9500 | 1.041122 |
|
||||
| 10000 | 1.046246 |
|
||||
| 10500 | 1.023033 |
|
||||
| 11000 | 1.031550 |
|
||||
| 11500 | 1.030448 |
|
||||
| 12000 | 1.031115 |
|
||||
| 12500 | 1.029919 |
|
||||
| 12800 | 1.029599 |
|
||||
|
||||
## Limitations
|
||||
|
||||
- The model generates ABC notation, not direct audio.
|
||||
- Some generations may be syntactically invalid ABC.
|
||||
- Some outputs may need manual cleanup before playback.
|
||||
- The model may reproduce fragments or patterns from the training data.
|
||||
- Musical quality varies; sampling multiple outputs and selecting the best one
|
||||
is recommended.
|
||||
|
||||
## Intended Use
|
||||
|
||||
This model is intended for experimentation with Irish folk tune generation,
|
||||
symbolic music modeling, and ABC notation text generation.
|
||||
|
||||
It is not intended for claims of originality or commercial music production
|
||||
without additional review for memorization and licensing concerns.
|
||||
|
||||
## Training Summary
|
||||
|
||||
This was trained as a practical free-GPU fine-tuning experiment after the
|
||||
original Karpathy `autoresearch` training setup proved unsuitable for Google
|
||||
Colab's free T4 GPU. Instead of training from scratch, this model uses GPT-2 as
|
||||
a pretrained base and adapts it to Irish ABC notation.
|
||||
3
assets/irish-gpt2-model.mp4
Normal file
3
assets/irish-gpt2-model.mp4
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c59d269274ce5fc4b9326da6dbbe41f5e6f5c54c22d35ddcfc882aa141386ceb
|
||||
size 11248150
|
||||
41
config.json
Normal file
41
config.json
Normal file
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"activation_function": "gelu_new",
|
||||
"add_cross_attention": false,
|
||||
"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,
|
||||
"pad_token_id": null,
|
||||
"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
|
||||
}
|
||||
},
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.8.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 50257
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50256,
|
||||
"eos_token_id": 50256,
|
||||
"transformers_version": "5.8.1"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:95b51b766a6db0e4d60a31e7312f1b80b6eddee2d6d2e839aca8b28a32616bd9
|
||||
size 497774208
|
||||
250306
tokenizer.json
Normal file
250306
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
13
tokenizer_config.json
Normal file
13
tokenizer_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<|endoftext|>",
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"is_local": false,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 1024,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
Reference in New Issue
Block a user