mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-04 21:30:07 +06:00
4397dfcb71
* smolvlm init * updates * fixing bugs * minimal run, no checks * minimal run, no checks * passing first check + adding url support * updating video dataloading logic * fixing image logic * trying modular, but fails * modular is working, changing processor to match PR comments and general transformers logic * fixing kwargs * offloading video loading logic to image_util * fixing circleci code formatting errors * fixing circleci code formatting errors * fixing circleci code formatting errors * fixing circleci code formatting errors * fixing circleci code formatting errors * fixing circleci code formatting errors * fixing circleci code formatting errors * fixing circleci code formatting errors * fixing circleci code formatting errors * fixing circleci code formatting errors * fixing circleci code formatting errors * fixing circleci code formatting errors * fixing circleci code formatting errors * fixing circleci code formatting errors * update * add idefics3-based tests * add keyword to all * add PreTrainedModel * updateing video loading logic * working inference * updates for PR comments * updates for PR comments * moving SmolVLMPretrainedModel higher to fix import error * CI test pass * CI test pass * removing lambda * CI test pass * CI test pass * CI test pass * CI test pass * CI test pass * CI test pass * processor tests * add example in docs * typo * fix copies * skip compile tests - sdpa for VisionTransformer * fix init * raise import error for num2words * update doc for FA2 * more doc fix * CI * updates for PR comments * Update docs/source/en/model_doc/smolvlm.md Co-authored-by: Pedro Cuenca <pedro@huggingface.co> * Update docs/source/en/model_doc/smolvlm.md Co-authored-by: Pedro Cuenca <pedro@huggingface.co> * Update docs/source/en/model_doc/smolvlm.md Co-authored-by: Joshua Lochner <admin@xenova.com> * Update docs/source/en/model_doc/smolvlm.md Co-authored-by: Pedro Cuenca <pedro@huggingface.co> * Update docs/source/en/model_doc/smolvlm.md Co-authored-by: Pedro Cuenca <pedro@huggingface.co> * fixing processor -- tokenizer not defined properly, (gpt2 tokenizer), and does not have the attributes of fake image token, etc * adding smolvlm to VQA models * removing vqa auto class * Update src/transformers/models/smolvlm/processing_smolvlm.py Co-authored-by: Joshua Lochner <admin@xenova.com> * removing smolvlmvisiontransformer from index.md * my bad, video processing had typos * fixing docs * renaming params in SmolVLMModel.inputs_merger * removing un-needed dtype/device in model forward * ruff for CI * update docs * Update docs/source/en/model_doc/smolvlm.md Co-authored-by: Pedro Cuenca <pedro@huggingface.co> * return cache position * return cache position * return cache also in modular * needed to run modular again * fix training tests * push vectorized inputs merger * format * format * reduce number of mappings * addressing PR comments * happy CI, happy me :) * skip non-nested images * adjust integration test for smaller GPUs * format * fix kwargs in chat template apply * skip this for now --------- Co-authored-by: raushan <raushan@huggingface.co> Co-authored-by: Pablo <pablo.montalvo.leroux@gmail.com> Co-authored-by: Pedro Cuenca <pedro@huggingface.co> Co-authored-by: Joshua Lochner <admin@xenova.com>
86 lines
1.8 KiB
Python
86 lines
1.8 KiB
Python
import time
|
|
|
|
import torch
|
|
|
|
from transformers import AutoModel, AutoTokenizer, pipeline
|
|
|
|
|
|
test_sentence = 'Do you [MASK] the muffin man?'
|
|
|
|
# for comparison
|
|
bert = pipeline('fill-mask', model = 'bert-base-uncased')
|
|
print('\n'.join([d['sequence'] for d in bert(test_sentence)]))
|
|
|
|
|
|
deberta = pipeline('fill-mask', model = 'microsoft/deberta-v3-base', model_kwargs={"legacy": False})
|
|
print('\n'.join([d['sequence'] for d in deberta(test_sentence)]))
|
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("microsoft/deberta-v3-base")
|
|
|
|
tokenized_dict = tokenizer(
|
|
["Is this working",], ["Not yet",],
|
|
return_tensors="pt"
|
|
)
|
|
|
|
deberta.model.forward = torch.compile(deberta.model.forward)
|
|
start=time.time()
|
|
deberta.model(**tokenized_dict)
|
|
end=time.time()
|
|
print(end-start)
|
|
|
|
|
|
start=time.time()
|
|
deberta.model(**tokenized_dict)
|
|
end=time.time()
|
|
print(end-start)
|
|
|
|
|
|
start=time.time()
|
|
deberta.model(**tokenized_dict)
|
|
end=time.time()
|
|
print(end-start)
|
|
|
|
|
|
model = AutoModel.from_pretrained('microsoft/deberta-base')
|
|
model.config.return_dict = False
|
|
model.config.output_hidden_states=False
|
|
input_tuple = (tokenized_dict['input_ids'], tokenized_dict['attention_mask'])
|
|
|
|
|
|
start=time.time()
|
|
traced_model = torch.jit.trace(model, input_tuple)
|
|
end=time.time()
|
|
print(end-start)
|
|
|
|
|
|
start=time.time()
|
|
traced_model(tokenized_dict['input_ids'], tokenized_dict['attention_mask'])
|
|
end=time.time()
|
|
print(end-start)
|
|
|
|
|
|
start=time.time()
|
|
traced_model(tokenized_dict['input_ids'], tokenized_dict['attention_mask'])
|
|
end=time.time()
|
|
print(end-start)
|
|
|
|
|
|
start=time.time()
|
|
traced_model(tokenized_dict['input_ids'], tokenized_dict['attention_mask'])
|
|
end=time.time()
|
|
print(end-start)
|
|
|
|
|
|
start=time.time()
|
|
traced_model(tokenized_dict['input_ids'], tokenized_dict['attention_mask'])
|
|
end=time.time()
|
|
print(end-start)
|
|
|
|
|
|
torch.jit.save(traced_model, "compiled_deberta.pt")
|
|
|
|
|
|
|
|
# my_script_module = torch.jit.script(model)
|