obi

/

deid_roberta_i2b2

like 22

Hello, I found this model to be very interesting. However, I am struggling to make it run locally when leveraging huggingface pipelines. I'm probably doing something wrong, but I feel like a hit a wall.

Here is my code:

from transformers import AutoTokenizer, AutoModelForMaskedLM
from transformers import pipeline

tokenizer = AutoTokenizer.from_pretrained("obi/deid_roberta_i2b2")
model = AutoModelForMaskedLM.from_pretrained("obi/deid_roberta_i2b2")

nlp = pipeline(model=model, tokenizer=tokenizer)

example = "My name is Wolfgang and I live in Berlin"

ner_results = nlp(example)
print(ner_results)

And here is the error stack I get:

RuntimeError Traceback (most recent call last)
Cell In[22], line 2
1 from transformers import pipeline
----> 2 nlp = pipeline(model=model, tokenizer=tokenizer)
4 example = "My name is Wolfgang and I live in Berlin"
6 ner_results = nlp(example)

File ~/hug/lib/python3.10/site-packages/transformers/pipelines/init.py:768, in pipeline(task, model, config, tokenizer, feature_extractor, image_processor, framework, revision, use_fast, token, device, device_map, torch_dtype, trust_remote_code, model_kwargs, pipeline_class, **kwargs)
766 if task is None and model is not None:
767 if not isinstance(model, str):
--> 768 raise RuntimeError(
769 "Inferring the task automatically requires to check the hub with a model_id defined as a str."
770 f"{model} is not a valid model_id."
771 )
772 task = get_task(model, use_auth_token)
774 # Retrieve the task

RuntimeError: Inferring the task automatically requires to check the hub with a model_id defined as a str.RobertaForMaskedLM(
(roberta): RobertaModel(
(embeddings): RobertaEmbeddings(
(word_embeddings): Embedding(50265, 1024, padding_idx=1)
(position_embeddings): Embedding(514, 1024, padding_idx=1)
(token_type_embeddings): Embedding(1, 1024)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(encoder): RobertaEncoder(
(layer): ModuleList(
(0-23): 24 x RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
)
(lm_head): RobertaLMHead(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(decoder): Linear(in_features=1024, out_features=50265, bias=True)
)
) is not a valid model_id.