Hello,
Experiencing the same issue with spacy 3.5.1 and transformers. Training config is generated by prodigy 1.11.11. Getting the error when either try to use this model with Prodigy with ner.correct or just load it into spacy with spacy.load(). Trying on the same machine as trainig.
Python version 3.7.12 it was trained in.
Also tried to load the model in Python 3.10.10.
freeze:
blis==0.7.9
catalogue==2.0.8
certifi==2022.12.7
charset-normalizer==3.1.0
click==8.1.3
confection==0.0.4
cupy-cuda113==10.6.0
cupy-cuda116==10.6.0
cymem==2.0.7
fastrlock==0.8.1
filelock==3.9.0
fr-core-news-sm @ https://github.com/explosion/spacy-models/releases/download/fr_core_news_sm-3.5.0/fr_core_news_sm-3.5.0-py3-none-any.whl
fr-dep-news-trf @ https://github.com/explosion/spacy-models/releases/download/fr_dep_news_trf-3.5.0/fr_dep_news_trf-3.5.0-py3-none-any.whl
huggingface-hub==0.13.1
idna==3.4
importlib-metadata==6.0.0
Jinja2==3.1.2
langcodes==3.3.0
MarkupSafe==2.1.2
murmurhash==1.0.9
numpy==1.21.6
nvidia-cublas-cu11==11.10.3.66
nvidia-cuda-nvrtc-cu11==11.7.99
nvidia-cuda-runtime-cu11==11.7.99
nvidia-cudnn-cu11==8.5.0.96
packaging==23.0
pathy==0.10.1
preshed==3.0.8
protobuf==3.20.3
pydantic==1.10.6
PyYAML==6.0
regex==2022.10.31
requests==2.28.2
sentencepiece==0.1.97
smart-open==6.3.0
spacy==3.5.1
spacy-alignments==0.9.0
spacy-legacy==3.0.12
spacy-loggers==1.0.4
spacy-transformers==1.2.2
srsly==2.4.6
thinc==8.1.9
tokenizers==0.13.2
torch==1.13.1
tqdm==4.65.0
transformers==4.26.1
typer==0.7.0
typing_extensions==4.4.0
urllib3==1.26.15
wasabi==1.1.1
zipp==3.15.0
config:
[paths]
train = null
dev = null
vectors = null
init_tok2vec = null
[system]
gpu_allocator = null
seed = 0
[nlp]
lang = "fr"
pipeline = ["tok2vec","transformer","morphologizer","parser","attribute_ruler","lemmatizer","ner"]
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
batch_size = 64
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
[components]
[components.attribute_ruler]
source = "fr_dep_news_trf"
[components.lemmatizer]
source = "fr_dep_news_trf"
[components.morphologizer]
source = "fr_dep_news_trf"
replace_listeners = ["model.tok2vec"]
[components.ner]
factory = "ner"
incorrect_spans_key = "incorrect_spans"
moves = null
scorer = {"@scorers":"spacy.ner_scorer.v1"}
update_with_oracle_cut_size = 100
[components.ner.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "ner"
extra_state_tokens = false
hidden_width = 64
maxout_pieces = 2
use_upper = true
nO = null
[components.ner.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}
upstream = "*"
[components.parser]
source = "fr_dep_news_trf"
replace_listeners = ["model.tok2vec"]
[components.tok2vec]
factory = "tok2vec"
[components.tok2vec.model]
@architectures = "spacy.Tok2Vec.v2"
[components.tok2vec.model.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = ${components.tok2vec.model.encode.width}
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
rows = [5000,1000,2500,2500]
include_static_vectors = false
[components.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 96
depth = 4
window_size = 1
maxout_pieces = 3
[components.transformer]
source = "fr_dep_news_trf"
[corpora]
[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
max_length = 0
gold_preproc = false
limit = 0
augmenter = null
[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
max_length = 0
gold_preproc = false
limit = 0
augmenter = null
[training]
train_corpus = "corpora.train"
dev_corpus = "corpora.dev"
seed = ${system:seed}
gpu_allocator = ${system:gpu_allocator}
dropout = 0.1
accumulate_gradient = 3
patience = 5000
max_epochs = 0
max_steps = 20000
eval_frequency = 1000
frozen_components = ["morphologizer","parser","attribute_ruler","lemmatizer"]
before_to_disk = null
annotating_components = []
before_update = null
[training.batcher]
@batchers = "spacy.batch_by_padded.v1"
discard_oversize = true
get_length = null
size = 2000
buffer = 256
[training.logger]
@loggers = "spacy.ConsoleLogger.v1"
progress_bar = false
[training.optimizer]
@optimizers = "Adam.v1"
beta1 = 0.9
beta2 = 0.999
L2_is_weight_decay = true
L2 = 0.01
grad_clip = 1.0
use_averages = true
eps = 0.00000001
[training.optimizer.learn_rate]
@schedules = "warmup_linear.v1"
warmup_steps = 250
total_steps = 20000
initial_rate = 0.00005
[training.score_weights]
pos_acc = null
morph_acc = null
morph_per_feat = null
dep_uas = null
dep_las = null
dep_las_per_type = null
sents_p = null
sents_r = null
sents_f = null
lemma_acc = null
ents_f = 1.0
ents_p = 0.0
ents_r = 0.0
ents_per_type = null
speed = 0.0
[pretraining]
[initialize]
vectors = ${paths.vectors}
init_tok2vec = ${paths.init_tok2vec}
vocab_data = null
lookups = null
before_init = null
after_init = null
[initialize.components]
[initialize.components.morphologizer]
[initialize.components.morphologizer.labels]
@readers = "spacy.read_labels.v1"
path = "spacy_training/labels/morphologizer.json"
require = false
[initialize.components.ner]
[initialize.components.ner.labels]
@readers = "spacy.read_labels.v1"
path = "spacy_training/labels/ner.json"
require = false
[initialize.components.parser]
[initialize.components.parser.labels]
@readers = "spacy.read_labels.v1"
path = "spacy_training/labels/parser.json"
require = false
[initialize.tokenizer]
error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-6-ddc3bbe33688> in <module>
----> 1 nlp = spacy.load('./')
~/trainings/env/lib/python3.7/site-packages/spacy/__init__.py in load(name, vocab, disable, enable, exclude, config)
58 enable=enable,
59 exclude=exclude,
---> 60 config=config,
61 )
62
~/trainings/env/lib/python3.7/site-packages/spacy/util.py in load_model(name, vocab, disable, enable, exclude, config)
442 return load_model_from_package(name, **kwargs) # type: ignore[arg-type]
443 if Path(name).exists(): # path to model data directory
--> 444 return load_model_from_path(Path(name), **kwargs) # type: ignore[arg-type]
445 elif hasattr(name, "exists"): # Path or Path-like to model data
446 return load_model_from_path(name, **kwargs) # type: ignore[arg-type]
~/trainings/env/lib/python3.7/site-packages/spacy/util.py in load_model_from_path(model_path, meta, vocab, disable, enable, exclude, config)
522 meta=meta,
523 )
--> 524 return nlp.from_disk(model_path, exclude=exclude, overrides=overrides)
525
526
~/trainings/env/lib/python3.7/site-packages/spacy/language.py in from_disk(self, path, exclude, overrides)
2123 # Convert to list here in case exclude is (default) tuple
2124 exclude = list(exclude) + ["vocab"]
-> 2125 util.from_disk(path, deserializers, exclude) # type: ignore[arg-type]
2126 self._path = path # type: ignore[assignment]
2127 self._link_components()
~/trainings/env/lib/python3.7/site-packages/spacy/util.py in from_disk(path, readers, exclude)
1367 # Split to support file names like meta.json
1368 if key.split(".")[0] not in exclude:
-> 1369 reader(path / key)
1370 return path
1371
~/trainings/env/lib/python3.7/site-packages/spacy/language.py in <lambda>(p, proc)
2118 continue
2119 deserializers[name] = lambda p, proc=proc: proc.from_disk( # type: ignore[misc]
-> 2120 p, exclude=["vocab"]
2121 )
2122 if not (path / "vocab").exists() and "vocab" not in exclude: # type: ignore[operator]
~/trainings/env/lib/python3.7/site-packages/spacy/pipeline/transition_parser.pyx in spacy.pipeline.transition_parser.Parser.from_disk()
~/trainings/env/lib/python3.7/site-packages/thinc/model.py in from_bytes(self, bytes_data)
617 msg = srsly.msgpack_loads(bytes_data)
618 msg = convert_recursive(is_xp_array, self.ops.asarray, msg)
--> 619 return self.from_dict(msg)
620
621 def from_disk(self, path: Union[Path, str]) -> "Model":
~/trainings/env/lib/python3.7/site-packages/thinc/model.py in from_dict(self, msg)
634 nodes = list(self.walk())
635 if len(msg["nodes"]) != len(nodes):
--> 636 raise ValueError("Cannot deserialize model: mismatched structure")
637 for i, node in enumerate(nodes):
638 info = msg["nodes"][i]
ValueError: Cannot deserialize model: mismatched structure