spiece.model file is not present upon saving the model after training .
I used this
python run_seq2seq_qa.py --model_name_or_path t5-small --dataset_name squad_v2 --context_column context --question_column question --answer_column answers --do_train --do_eval --per_device_train_batch_size 12 --learning_rate 3e-5 --num_train_epochs 1 --max_seq_length 384 --doc_stride 128 --output_dir /trained_model/debug_seq2seq_squad/ --max_train_samples 50 --max_eval_samples 50
to run the run_seq2seq_qa.py from transformers git examples but cannot be used for inferencing.
Files saved after training :
generation_config.json
config.json
all_results.json
train_results.json
special_tokens_map.json
eval_results.json
tokenizer.json
tokenizer_config.json
runs
pytorch_model.bin
training_args.bin
trainer_state.json
code used :
from transformers import T5ForConditionalGeneration, T5Tokenizer
def run_t5_squad_example(model_dir, question, context):
# Load the T5 model and tokenizer
model = T5ForConditionalGeneration.from_pretrained(model_dir)
tokenizer = T5Tokenizer.from_pretrained(model_dir)
# Prepare the input
input_text = f"question: {question} context: {context}"
input_ids = tokenizer.encode(input_text, return_tensors="pt")
# Generate the answer
output = model.generate(input_ids)
answer = tokenizer.decode(output[0], skip_special_tokens=True)
return answer
model_directory = “t5_model”
print(type(model_directory))
question = “What is the capital of France?”
context = “Paris is the capital of France.”
answer = run_t5_squad_example(model_directory, question, context)
print(“Answer:”, answer)
ERROR received:
<class ‘str’>
┌───────────────────── Traceback (most recent call last) ─────────────────────┐
│ C:\Users\admin\Desktop\True_Vision\NLP\Question_Answering\question-answerin │
│ g-transformers-git\model_testing.py:23 in │
│ │
│ 20 question = “What is the capital of France?” │
│ 21 context = “Paris is the capital of France.” │
│ 22 │
│ > 23 answer = run_t5_squad_example(model_directory, question, context) │
│ 24 print(“Answer:”, answer) │
│ 25 │
│ 26 from transformers import T5ForConditionalGeneration, T5Tokenizer │
│ │
│ C:\Users\admin\Desktop\True_Vision\NLP\Question_Answering\question-answerin │
│ g-transformers-git\model_testing.py:6 in run_t5_squad_example │
│ │
│ 3 def run_t5_squad_example(model_dir, question, context): │
│ 4 │ # Load the T5 model and tokenizer │
│ 5 │ model = T5ForConditionalGeneration.from_pretrained(model_dir) │
│ > 6 │ tokenizer = T5Tokenizer.from_pretrained(model_dir) │
│ 7 │ │
│ 8 │ # Prepare the input │
│ 9 │ input_text = f"question: {question} context: {context}" │
│ │
│ C:\Users\admin\Desktop\env\lib\site-packages\transformers\tokenization_util │
│ s_base.py:1825 in from_pretrained │
│ │
│ 1822 │ │ │ else: │
│ 1823 │ │ │ │ logger.info(f"loading file {file_path} from cache at │
│ 1824 │ │ │
│ > 1825 │ │ return cls._from_pretrained( │
│ 1826 │ │ │ resolved_vocab_files, │
│ 1827 │ │ │ pretrained_model_name_or_path, │
│ 1828 │ │ │ init_configuration, │
│ │
│ C:\Users\admin\Desktop\env\lib\site-packages\transformers\tokenization_util │
│ s_base.py:1988 in _from_pretrained │
│ │
│ 1985 │ │ │
│ 1986 │ │ # Instantiate tokenizer. │
│ 1987 │ │ try: │
│ > 1988 │ │ │ tokenizer = cls(*init_inputs, **init_kwargs) │
│ 1989 │ │ except OSError: │
│ 1990 │ │ │ raise OSError( │
│ 1991 │ │ │ │ "Unable to load vocabulary from file. " │
│ │
│ C:\Users\admin\Desktop\env\lib\site-packages\transformers\models\t5\tokeniz │
│ ation_t5.py:154 in init │
│ │
│ 151 │ │ self._extra_ids = extra_ids │
│ 152 │ │ │
│ 153 │ │ self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kw │
│ > 154 │ │ self.sp_model.Load(vocab_file) │
│ 155 │ │
│ 156 │ @staticmethod │
│ 157 │ def eventually_correct_t5_max_length(pretrained_model_name_or_pa │
│ │
│ C:\Users\admin\Desktop\env\lib\site-packages\sentencepiece_init.py:905 │
│ in Load │
│ │
│ 902 │ │ raise RuntimeError('model_file and model_proto must be exclu │
│ 903 │ if model_proto: │
│ 904 │ │ return self.LoadFromSerializedProto(model_proto) │
│ > 905 │ return self.LoadFromFile(model_file) │
│ 906 │
│ 907 │
│ 908 # Register SentencePieceProcessor in sentencepiece: │
│ │
│ C:\Users\admin\Desktop\env\lib\site-packages\sentencepiece_init.py:310 │
│ in LoadFromFile │
│ │
│ 307 │ │ return _sentencepiece.SentencePieceProcessor_serialized_mode │
│ 308 │ │
│ 309 │ def LoadFromFile(self, arg): │
│ > 310 │ │ return _sentencepiece.SentencePieceProcessor_LoadFromFile(se │
│ 311 │ │
│ 312 │ def _EncodeAsIds(self, text, enable_sampling, nbest_size, alpha, │
│ 313 │ │ return _sentencepiece.SentencePieceProcessor__EncodeAsIds(se │
└─────────────────────────────────────────────────────────────────────────────┘
TypeError: not a string
model directory is not a string.
i have checked that the model directory is of string type .