search

AI4Bharat / IndicBERT

Pretraining, fine-tuning and evaluation scripts for IndicBERT-v2 and IndicXTREME
https://ai4bharat.iitm.ac.in/language-understanding
MIT License
73 stars 13 forks source link

The model 'AlbertModel' is not supported for sentiment-analysis #13

Open alvynabranches opened 1 month ago

alvynabranches commented 1 month ago

Code

from transformers import pipeline, AutoModel, AutoTokenizer

model_id = "ai4bharat/indic-bert"
tokenizer = AutoTokenizer.from_pretrained(model_id, keep_accents=True)
model = AutoModel.from_pretrained(model_id)
pipe = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)

print(pipe("मी कॉलेजमध्ये आहे"))

Error

The model 'AlbertModel' is not supported for sentiment-analysis. Supported models are ['AlbertForSequenceClassification', 'BartForSequenceClassification', 'BertForSequenceClassification', 'BigBirdForSequenceClassification', 'BigBirdPegasusForSequenceClassification', 'BioGptForSequenceClassification', 'BloomForSequenceClassification', 'CamembertForSequenceClassification', 'CanineForSequenceClassification', 'LlamaForSequenceClassification', 'ConvBertForSequenceClassification', 'CTRLForSequenceClassification', 'Data2VecTextForSequenceClassification', 'DebertaForSequenceClassification', 'DebertaV2ForSequenceClassification', 'DistilBertForSequenceClassification', 'ElectraForSequenceClassification', 'ErnieForSequenceClassification', 'ErnieMForSequenceClassification', 'EsmForSequenceClassification', 'FalconForSequenceClassification', 'FlaubertForSequenceClassification', 'FNetForSequenceClassification', 'FunnelForSequenceClassification', 'GemmaForSequenceClassification', 'Gemma2ForSequenceClassification', 'GPT2ForSequenceClassification', 'GPT2ForSequenceClassification', 'GPTBigCodeForSequenceClassification', 'GPTNeoForSequenceClassification', 'GPTNeoXForSequenceClassification', 'GPTJForSequenceClassification', 'IBertForSequenceClassification', 'JambaForSequenceClassification', 'JetMoeForSequenceClassification', 'LayoutLMForSequenceClassification', 'LayoutLMv2ForSequenceClassification', 'LayoutLMv3ForSequenceClassification', 'LEDForSequenceClassification', 'LiltForSequenceClassification', 'LlamaForSequenceClassification', 'LongformerForSequenceClassification', 'LukeForSequenceClassification', 'MarkupLMForSequenceClassification', 'MBartForSequenceClassification', 'MegaForSequenceClassification', 'MegatronBertForSequenceClassification', 'MistralForSequenceClassification', 'MixtralForSequenceClassification', 'MobileBertForSequenceClassification', 'MPNetForSequenceClassification', 'MptForSequenceClassification', 'MraForSequenceClassification', 'MT5ForSequenceClassification', 'MvpForSequenceClassification', 'NemotronForSequenceClassification', 'NezhaForSequenceClassification', 'NystromformerForSequenceClassification', 'OpenLlamaForSequenceClassification', 'OpenAIGPTForSequenceClassification', 'OPTForSequenceClassification', 'PerceiverForSequenceClassification', 'PersimmonForSequenceClassification', 'PhiForSequenceClassification', 'Phi3ForSequenceClassification', 'PLBartForSequenceClassification', 'QDQBertForSequenceClassification', 'Qwen2ForSequenceClassification', 'Qwen2MoeForSequenceClassification', 'ReformerForSequenceClassification', 'RemBertForSequenceClassification', 'RobertaForSequenceClassification', 'RobertaPreLayerNormForSequenceClassification', 'RoCBertForSequenceClassification', 'RoFormerForSequenceClassification', 'SqueezeBertForSequenceClassification', 'StableLmForSequenceClassification', 'Starcoder2ForSequenceClassification', 'T5ForSequenceClassification', 'TapasForSequenceClassification', 'TransfoXLForSequenceClassification', 'UMT5ForSequenceClassification', 'XLMForSequenceClassification', 'XLMRobertaForSequenceClassification', 'XLMRobertaXLForSequenceClassification', 'XLNetForSequenceClassification', 'XmodForSequenceClassification', 'YosoForSequenceClassification'].
Traceback (most recent call last):
  File "/Users/user/kok/marathi.py", line 7, in <module>
    print(pipe("मी कॉलेजमध्ये आहे"))
          ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/lib/python3.12/site-packages/transformers/pipelines/text_classification.py", line 156, in __call__
    result = super().__call__(*inputs, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/lib/python3.12/site-packages/transformers/pipelines/base.py", line 1257, in __call__
    return self.run_single(inputs, preprocess_params, forward_params, postprocess_params)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/lib/python3.12/site-packages/transformers/pipelines/base.py", line 1265, in run_single
    outputs = self.postprocess(model_outputs, **postprocess_params)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/lib/python3.12/site-packages/transformers/pipelines/text_classification.py", line 204, in postprocess
    outputs = model_outputs["logits"][0]
              ~~~~~~~~~~~~~^^^^^^^^^^
  File "/opt/homebrew/lib/python3.12/site-packages/transformers/utils/generic.py", line 431, in __getitem__
    return inner_dict[k]
           ~~~~~~~~~~^^^
KeyError: 'logits'