Spaces:
Runtime error
Runtime error
File size: 6,360 Bytes
1f39ae1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 |
#!/usr/bin/env python3
"""
Hugging Face model configuration for TagTransformer
"""
from transformers import PretrainedConfig
from typing import Dict, Any, Optional
class TagTransformerConfig(PretrainedConfig):
"""Configuration class for TagTransformer model"""
model_type = "tag_transformer"
def __init__(
self,
src_vocab_size: int = 1000,
trg_vocab_size: int = 1000,
embed_dim: int = 256,
nb_heads: int = 4,
src_hid_size: int = 1024,
src_nb_layers: int = 4,
trg_hid_size: int = 1024,
trg_nb_layers: int = 4,
dropout_p: float = 0.1,
tie_trg_embed: bool = True,
label_smooth: float = 0.1,
max_length: int = 100,
nb_attr: int = 0,
**kwargs
):
super().__init__(**kwargs)
self.src_vocab_size = src_vocab_size
self.trg_vocab_size = trg_vocab_size
self.embed_dim = embed_dim
self.nb_heads = nb_heads
self.src_hid_size = src_hid_size
self.src_nb_layers = src_nb_layers
self.trg_hid_size = trg_hid_size
self.trg_nb_layers = trg_nb_layers
self.dropout_p = dropout_p
self.tie_trg_embed = tie_trg_embed
self.label_smooth = label_smooth
self.max_length = max_length
self.nb_attr = nb_attr
class TagTransformerForMorphologicalReinflection:
"""Hugging Face model wrapper for TagTransformer"""
def __init__(self, config: TagTransformerConfig):
self.config = config
self.model = None
def from_pretrained(self, model_path: str):
"""Load model from pretrained checkpoint"""
import torch
from transformer import TagTransformer
# Load configuration
config = TagTransformerConfig.from_pretrained(model_path)
# Create model
model = TagTransformer(
src_vocab_size=config.src_vocab_size,
trg_vocab_size=config.trg_vocab_size,
embed_dim=config.embed_dim,
nb_heads=config.nb_heads,
src_hid_size=config.src_hid_size,
src_nb_layers=config.src_nb_layers,
trg_hid_size=config.trg_hid_size,
trg_nb_layers=config.trg_nb_layers,
dropout_p=config.dropout_p,
tie_trg_embed=config.tie_trg_embed,
label_smooth=config.label_smooth,
nb_attr=config.nb_attr,
src_c2i={}, # Will be loaded separately
trg_c2i={}, # Will be loaded separately
attr_c2i={},
)
# Load state dict
state_dict = torch.load(f"{model_path}/pytorch_model.bin", map_location='cpu')
model.load_state_dict(state_dict)
self.model = model
return self
def save_pretrained(self, save_path: str):
"""Save model in Hugging Face format"""
import torch
import json
from pathlib import Path
save_path = Path(save_path)
save_path.mkdir(parents=True, exist_ok=True)
# Save model state dict
torch.save(self.model.state_dict(), save_path / "pytorch_model.bin")
# Save configuration
self.config.save_pretrained(save_path)
# Save vocabularies if available
if hasattr(self.model, 'src_c2i') and self.model.src_c2i:
with open(save_path / "src_vocab.json", "w") as f:
json.dump(self.model.src_c2i, f, indent=2)
if hasattr(self.model, 'trg_c2i') and self.model.trg_c2i:
with open(save_path / "tgt_vocab.json", "w") as f:
json.dump(self.model.trg_c2i, f, indent=2)
def generate(self, input_ids, max_length: int = 100, **kwargs):
"""Generate predictions for morphological reinflection"""
import torch
self.model.eval()
with torch.no_grad():
# Simple greedy generation
# This is a simplified version - you might want to implement beam search
output = self.model(input_ids, **kwargs)
predictions = torch.argmax(output, dim=-1)
return predictions
def create_model_card(model_name: str, dataset_name: str, task: str = "morphological-reinflection") -> str:
"""Create a model card for Hugging Face Hub"""
model_card = f"""---
license: mit
tags:
- morphological-reinflection
- transformer
- nlp
- linguistics
datasets:
- {dataset_name}
metrics:
- accuracy
- bleu
model-index:
- name: {model_name}
results:
- task:
type: morphological-reinflection
name: Morphological Reinflection
dataset:
type: {dataset_name}
name: {dataset_name}
metrics:
- type: accuracy
value: 0.0
name: Accuracy
- type: bleu
value: 0.0
name: BLEU Score
---
# {model_name}
This model is a TagTransformer for morphological reinflection tasks. It can transform words from one morphological form to another based on linguistic features.
## Model Description
- **Model type**: TagTransformer
- **Task**: Morphological Reinflection
- **Language**: Multiple languages (depends on training data)
- **Architecture**: Encoder-Decoder Transformer with special feature embeddings
## Usage
```python
from transformers import AutoModel, AutoTokenizer
# Load model and tokenizer
model = AutoModel.from_pretrained("{model_name}")
tokenizer = AutoTokenizer.from_pretrained("{model_name}")
# Example usage
input_text = "example input"
output = model.generate(input_text)
```
## Training Data
This model was trained on the {dataset_name} dataset.
## Training Procedure
The model was trained using:
- Optimizer: AdamW
- Learning rate: 0.001
- Batch size: 400
- Mixed precision training
- Gradient accumulation
## Evaluation
The model achieves the following results on the test set:
- Accuracy: TBD
- BLEU Score: TBD
## Limitations and Bias
This model may have limitations in:
- Handling rare morphological patterns
- Cross-lingual generalization
- Domain-specific terminology
## Citation
```bibtex
@misc{{{model_name.lower().replace('-', '_')},
title={{{model_name}}},
author={{Your Name}},
year={{2024}},
publisher={{Hugging Face}},
howpublished={{\\url{{https://huggingface.co/{model_name}}}}}
}}
```
"""
return model_card
|