35 Model Hub entries fail AutoConfig

Here is what I ran:

from transformers.hf_api import HfApi
from tqdm import tqdm
import pandas as pd

model_list = HfApi().model_list()
model_ids = [x.modelId for x in model_list]

from transformers import AutoConfig


def check_hub(cls, model_ids):
    results = {}
    failure_data = {}
    for m in tqdm(model_ids):
        try:
            cls.from_pretrained(m)
            results[m] = True
        except Exception as e:
            failure_data[m] = e.args
            results[m] = False
    return results, failure_data
results, failure_data = check_hub(AutoConfig, model_ids)
print(failure_data)

Results:

{'DeBERTa/base': ('Unrecognized model in DeBERTa/base. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'DeBERTa/large': ('Unrecognized model in DeBERTa/large. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'Itcast/cnc_output': ('Unrecognized model in Itcast/cnc_output. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'Narsil/fr_pretrained': ('Unrecognized model in Narsil/fr_pretrained. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'Narsil/pretrained': ('Unrecognized model in Narsil/pretrained. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'Narsil/pretrained2': ('Unrecognized model in Narsil/pretrained2. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'abryee/TigXLNet': ('`d_head` (64) should be equal to `d_model // n_head` (48)',),
 'adamlin/ClinicalBert_all_notes': ('Unrecognized model in adamlin/ClinicalBert_all_notes. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'adamlin/ClinicalBert_disch': ('Unrecognized model in adamlin/ClinicalBert_disch. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'adamlin/NCBI_BERT_pubmed_mimic_uncased_base_transformers': ('Unrecognized model in adamlin/NCBI_BERT_pubmed_mimic_uncased_base_transformers. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'adamlin/NCBI_BERT_pubmed_mimic_uncased_large_transformers': ('Unrecognized model in adamlin/NCBI_BERT_pubmed_mimic_uncased_large_transformers. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'dccuchile/cased': ('Unrecognized model in dccuchile/cased. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'dccuchile/uncased': ('Unrecognized model in dccuchile/uncased. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'djstrong/bg_cs_pl_ru_cased_L-12_H-768_A-12': ('Unrecognized model in djstrong/bg_cs_pl_ru_cased_L-12_H-768_A-12. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'facebook/dpr-ctx_encoder-single-nq-base': ('dpr',),
 'facebook/dpr-question_encoder-single-nq-base': ('dpr',),
 'facebook/dpr-reader-single-nq-base': ('dpr',),
 'healx/gpt-2-pubmed-large': ('Unrecognized model in healx/gpt-2-pubmed-large. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'healx/gpt-2-pubmed-medium': ('Unrecognized model in healx/gpt-2-pubmed-medium. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'hfl/rbt3': ('Unrecognized model in hfl/rbt3. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'hfl/rbtl3': ('Unrecognized model in hfl/rbtl3. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'microsoft/unilm-base-cased': ('Unrecognized model in microsoft/unilm-base-cased. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'microsoft/unilm-large-cased': ('Unrecognized model in microsoft/unilm-large-cased. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'mrm8488/prunebert-base-uncased-finepruned-topK-squadv2': ('masked_bert',),
 'mrm8488/prunebert-multi-uncased-finepruned-l0-reg-tydiqa-for-xqa': ('masked_bert',),
 'mrm8488/prunebert-multi-uncased-finepruned-magnitude-tydiqa-for-xqa': ('masked_bert',),
 'mrm8488/prunebert-multi-uncased-finepruned-soft-movement-tydiqa-for-xqa': ('masked_bert',),
 'mrm8488/prunebert-multi-uncased-finepruned-topK-tydiqa-for-xqa': ('masked_bert',),
 'mrm8488/prunebert-multi-uncased-finepruned-tydiqa-for-xqa': ('masked_bert',),
 'oda/music5': ('Unrecognized model in oda/music5. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'pertschuk/0_RoBERTa': ('Unrecognized model in pertschuk/0_RoBERTa. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'radha1258/save': ('Unrecognized model in radha1258/save. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'sshleifer/blenderbot-3B': ('blenderbot',),
 'subbareddyiiit/iiit': ('Unrecognized model in subbareddyiiit/iiit. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',),
 'subbareddyiiit/tftelugu': ('Unrecognized model in subbareddyiiit/tftelugu. Should have a `model_type` key in its config.json, or contain one of the following strings in its name: retribert, t5, mobilebert, distilbert, albert, camembert, xlm-roberta, marian, mbart, bart, reformer, longformer, roberta, flaubert, bert, openai-gpt, gpt2, transfo-xl, xlnet, xlm, ctrl, electra, encoder-decoder',)}

[patrickvonplaten]

Is there some way for us to, like, change the config file and make a pull request? I’m not 100% sure how to find the Adam Lin that added ClinicalBert_all_notes and ask him to change it himself…

I think we would like to enable pull requests on model repositories (cc @julien-c)

[LysandreJik]

@drussellmrichie, on the model hub 😃 https://huggingface.co/models