Traceback (most recent call last):

[Dontmindmes]

Hello when i execute the following code i get the following error (Windows 11) `

import torch from fairseq.models.transformer_lm import TransformerLanguageModel m = TransformerLanguageModel.from_pretrained( "checkpoints", "checkpoint_avg.pt", "data", tokenizer='moses', bpe='fastbpe', bpe_codes="data/bpecodes", min_len=100, max_len_b=1024) m.cuda() src_tokens = m.encode("COVID-19 is") generate = m.generate([src_tokens], beam=5)[0] output = m.decode(generate[0]["tokens"]) print(output)

`

`

2023-02-22 19:39:41 | INFO | fairseq.file_utils | loading archive file checkpoints 2023-02-22 19:39:41 | INFO | fairseq.file_utils | loading archive file data Traceback (most recent call last): File "C:\Users\Gilgamesh\Documents\Advanced A.I\Bio\code\BioGPT\bio.py", line 3, in m = TransformerLanguageModel.from_pretrained( File "C:\Python310\lib\site-packages\fairseq\models\fairseq_model.py", line 267, in from_pretrained x = hub_utils.from_pretrained( File "C:\Python310\lib\site-packages\fairseq\hub_utils.py", line 73, in from_pretrained models, args, task = checkpoint_utils.load_model_ensemble_and_task( File "C:\Python310\lib\site-packages\fairseq\checkpoint_utils.py", line 432, in load_model_ensemble_and_task task = tasks.setup_task(cfg.task) File "C:\Python310\lib\site-packages\fairseq\tasks__init__.py", line 42, in setup_task assert ( AssertionError: Could not infer task type from {'_name': 'language_modeling_prompt', 'data': 'data', 'sample_break_mode': 'none', 'tokens_per_sample': 2048, 'output_dictionary_size': -1, 'self_target': False, 'future_target': False, 'past_target': False, 'add_bos_token': False, 'max_target_positions': 2048, 'shorten_method': 'none', 'shorten_data_split_list': '', 'pad_to_fixed_length': False, 'pad_to_fixed_bsz': False, 'seed': 1, 'batch_size': None, 'batch_size_valid': None, 'dataset_impl': None, 'data_buffer_size': 10, 'tpu': False, 'use_plasma_view': False, 'plasma_path': '/tmp/plasma', 'source_lang': None, 'target_lang': None, 'max_source_positions': 1900, 'manual_prompt': None, 'learned_prompt': 9, 'learned_prompt_pattern': 'learned', 'prefix': False, 'sep_token': ''}. Available argparse tasks: dict_keys(['audio_pretraining', 'audio_finetuning', 'cross_lingual_lm', 'denoising', 'speech_to_text', 'text_to_speech', 'frm_text_to_speech', 'hubert_pretraining', 'language_modeling', 'legacy_masked_lm', 'masked_lm', 'multilingual_denoising', 'multilingual_language_modeling', 'multilingual_masked_lm', 'speech_unit_modeling', 'translation', 'multilingual_translation', 'online_backtranslation', 'semisupervised_translation', 'sentence_prediction', 'sentence_prediction_adapters', 'sentence_ranking', 'simul_speech_to_text', 'simul_text_to_text', 'speech_to_speech', 'translation_from_pretrained_bart', 'translation_from_pretrained_xlm', 'translation_lev', 'translation_multi_simple_epoch', 'dummy_lm', 'dummy_masked_lm', 'dummy_mt']). Available hydra tasks: dict_keys(['audio_pretraining', 'audio_finetuning', 'hubert_pretraining', 'language_modeling', 'masked_lm', 'multilingual_language_modeling', 'speech_unit_modeling', 'translation', 'sentence_prediction', 'sentence_prediction_adapters', 'simul_text_to_text', 'translation_from_pretrained_xlm', 'translation_lev', 'dummy_lm', 'dummy_masked_lm'])

`

[Kristian-A]

I am getting the same issue when trying to run QA-PubMedQA-BioGPT-Large model using:

m = TransformerLanguageModel.from_pretrained(
    "checkpoints/QA-PubMedQA-BioGPT-Large",
    "checkpoint_avg.pt",
    "data",
    tokenizer="moses",
    bpe="fastbpe",
    bpe_codes="data/bpecodes",
    min_len=100,
    max_len_b=1024,
)

[Dontmindmes]

I am getting the same issue when trying to run QA-PubMedQA-BioGPT-Large model using:

m = TransformerLanguageModel.from_pretrained(
    "checkpoints/QA-PubMedQA-BioGPT-Large",
    "checkpoint_avg.pt",
    "data",
    tokenizer="moses",
    bpe="fastbpe",
    bpe_codes="data/bpecodes",
    min_len=100,
    max_len_b=1024,
)

What was the error you were getting

[Kristian-A]

File "/Users/kristian/Desktop/medical-gpt/biogpt/BioGPT/test.py", line 4, in <module>
    m = TransformerLanguageModel.from_pretrained(
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/fairseq/models/fairseq_model.py", line 267, in from_pretrained
    x = hub_utils.from_pretrained(
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/fairseq/hub_utils.py", line 73, in from_pretrained
    models, args, task = checkpoint_utils.load_model_ensemble_and_task(
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/fairseq/checkpoint_utils.py", line 432, in load_model_ensemble_and_task
    task = tasks.setup_task(cfg.task)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/fairseq/tasks/__init__.py", line 42, in setup_task
    assert (
AssertionError: Could not infer task type from {'_name': 'language_modeling_prompt', 'data': 'data', 
'sample_break_mode': 'none', 'tokens_per_sample': 2048, 'output_dictionary_size': -1, 'self_target': False, 'future_target': 
False, 'past_target': False, 'add_bos_token': False, 'max_target_positions': 2048, 'shorten_method': 'none', 
'shorten_data_split_list': '', 'pad_to_fixed_length': False, 'pad_to_fixed_bsz': False, 'seed': 1, 'batch_size': None, 
'batch_size_valid': None, 'dataset_impl': None, 'data_buffer_size': 10, 'tpu': False, 'use_plasma_view': False, 
'plasma_path': '/tmp/plasma', 'source_lang': None, 'target_lang': None, 'max_source_positions': 1900, 'manual_prompt': 
None, 'learned_prompt': 9, 'learned_prompt_pattern': 'learned', 'prefix': False, 'sep_token': '<seqsep>'}. Available 
argparse tasks: dict_keys(['sentence_prediction', 'sentence_prediction_adapters', 'speech_unit_modeling', 
'hubert_pretraining', 'denoising', 'multilingual_denoising', 'translation', 'multilingual_translation', 
'translation_from_pretrained_bart', 'translation_lev', 'language_modeling', 'speech_to_text', 'legacy_masked_lm', 
'text_to_speech', 'speech_to_speech', 'online_backtranslation', 'simul_speech_to_text', 'simul_text_to_text', 
'audio_pretraining', 'semisupervised_translation', 'frm_text_to_speech', 'cross_lingual_lm', 
'translation_from_pretrained_xlm', 'multilingual_language_modeling', 'audio_finetuning', 'masked_lm', 'sentence_ranking',
 'translation_multi_simple_epoch', 'multilingual_masked_lm', 'dummy_lm', 'dummy_masked_lm', 'dummy_mt']). Available 
hydra tasks: dict_keys(['sentence_prediction', 'sentence_prediction_adapters', 'speech_unit_modeling', 
'hubert_pretraining', 'translation', 'translation_lev', 'language_modeling', 'simul_text_to_text', 'audio_pretraining', 
'translation_from_pretrained_xlm', 'multilingual_language_modeling', 'audio_finetuning', 'masked_lm', 'dummy_lm', 
'dummy_masked_lm'])

[mx60s]

Hello @Kristian-A @Dontmindmes, were you ever able to fix this?

I'm having the same issue. I've fine tuned BioGPT on a relation extraction task, and the training with fairseq was just fine, but now I can't evaluate it.

[shodhak]

Was anyone able to solve this?