Trying to fine tune a transformer with spacy, getting a weird error despite copy-pasting from docs

Everytime I run the below code with the corresponding config I get the following error, telling me I used the wrong model architecture name despite listing that exact name in "available names" in the error message. This is my first time doing a custom config with spacy so I tried to follow the docs closely and keep it simple. still very new to this:

RegistryError: [E893] Could not find function '"spacy-transformers.TransformerModel.v3",' in function registry 'architectures'. If you're using a custom function, make sure the code is available. If the function is provided by a third-party package, e.g. spacy-transformers, make sure the package is installed in your environment.

Available names: spacy-legacy.CharacterEmbed.v1, spacy-legacy.EntityLinker.v1, spacy-legacy.HashEmbedCNN.v1, spacy-legacy.MaxoutWindowEncoder.v1, spacy-legacy.MishWindowEncoder.v1, spacy-legacy.MultiHashEmbed.v1, spacy-legacy.Tagger.v1, spacy-legacy.TextCatBOW.v1, spacy-legacy.TextCatCNN.v1, spacy-legacy.TextCatEnsemble.v1, spacy-legacy.Tok2Vec.v1, spacy-legacy.TransitionBasedParser.v1, spacy-transformers.Tok2VecTransformer.v1, spacy-transformers.Tok2VecTransformer.v2, spacy-transformers.Tok2VecTransformer.v3, spacy-transformers.TransformerListener.v1, spacy-transformers.TransformerModel.v1, spacy-transformers.TransformerModel.v2, spacy-**transformers.TransformerModel.v3**, spacy.CharacterEmbed.v2, spacy.EntityLinker.v2, spacy.HashEmbedCNN.v2, spacy.MaxoutWindowEncoder.v2, spacy.MishWindowEncoder.v2, spacy.MultiHashEmbed.v2, spacy.PretrainCharacters.v1, spacy.PretrainVectors.v1, spacy.SpanCategorizer.v1, spacy.SpanFinder.v1, spacy.Tagger.v2, spacy.TextCatBOW.v2, spacy.TextCatBOW.v3, spacy.TextCatCNN.v2, spacy.TextCatEnsemble.v2, spacy.TextCatLowData.v1, spacy.TextCatParametricAttention.v1, spacy.TextCatReduce.v1, spacy.Tok2Vec.v2, spacy.Tok2VecListener.v1, spacy.TorchBiLSTMEncoder.v1, spacy.TransitionBasedParser.v2

The training code:
train("./modelConfigs/configTransformer.cfg",
output_path='./clinBert_Embedd_CAT',
overrides={"paths.train": "./trainData/trainingSet_textcat.spacy",
"paths.dev": "./trainData/testSet_textcat.spacy", "components.transformer.model.name" : "./Bio_ClinicalBERT",
"training.max_epochs": 15})

My config:
[paths]
train = ""
dev = ""
raw = null
init_tok2vec = null
vectors = null

[system]
gpu_allocator = "pytorch"
seed = 0

[nlp]
lang = "en"
pipeline = ["transformer", "doc_vector_producer"]
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
before_creation = null
after_creation = null
after_pipeline_creation = null
disabled = []

[components]
[components.transformer]
factory = "transformer"

[components.transformer.model]
@architectures= "spacy-transformers.TransformerModel.v3",
name= "./Bio_ClinicalBERT"
tokenizer_config = {"use_fast": true}
transformer_config = {}
mixed_precision = true
grad_scaler_config = {"init_scale": 32768}

[components.transformer.model.get_spans]
@span_getters = "spacy-transformers.strided_spans.v1"
window = 128
stride = 96

[components.doc_vector_producer]
factory = "tok2vec"

[components.doc_vector_producer.model]
@architectures = "spacy-transformers.TransformerListener.v1"
upstream = "transformer"
pooling = {"@layers":"reduce_mean.v1"}

grad_factor = 0.0

[components.doc_vector_producer.model.pooling]
@layers = "reduce_mean.v1"

[corpora]
[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
max_length = 512
gold_preproc = false
limit = 0
augmenter = null

[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
max_length = 512
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 = 1
patience = 1600
max_epochs = 60
eval_frequency = 200

[training.score_weights]
cats_SIMILAR_f = 1.0
cats_NOT_SIMILAR_f = 1.0

[training.batcher]
@batchers = "spacy.batch_by_padded.v1"
discard_oversize = true
size = 1000
buffer = 256
get_length = null

[training.logger]
@loggers = "spacy.ConsoleLogger.v1"
progress_bar = true

[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 = false
eps = 0.00000001

[training.optimizer.learn_rate]
@schedules = "warmup_linear.v1"
warmup_steps = 250
total_steps = 10000
initial_rate = 2e-5

[pretraining]

[initialize]
vectors = ${paths.vectors}
init_tok2vec = ${paths.init_tok2vec}
vocab_data = null
lookups = null
before_init = null
after_init = null

[initialize.components]

[initialize.tokenizer]

## Your Environment
## Info about spaCy

- **spaCy version:** 3.8.7
- **Platform:** Linux-5.10.0-34-cloud-amd64-x86_64-with-glibc2.31
- **Python version:** 3.10.16
- **Pipelines:** en_core_web_sm (3.8.0)