直接运行src/text_generation_hf.py文件，会报错，能提供下transformers版本嘛

[Gu-Penghui]

Traceback (most recent call last):
File "/home/litao/ScienGU/sciengu_cpmbee/sciengu/test.py", line 15, in
tokenizer = AutoTokenizer.from_pretrained("openbmb/cpm-bee-10b", trust_remote_code=True)
File "/home/anaconda3/envs/litao_sciengu_cpmbee/lib/python3.9/site-packages/transformers/models/auto/tokenization_auto.py", line 719, in from_pretrained
raise ValueError(
ValueError: Unrecognized configuration class <class 'transformers_modules.openbmb.cpm-bee-10b.02840c59e956e5502ef4f8274ae14ab11575db58.configuration_cpmbee.CpmBeeConfig'> to build an AutoTokenizer.
Model type should be one of AlbertConfig, AlignConfig, BartConfig, BertConfig, BertGenerationConfig, BigBirdConfig, BigBirdPegasusConfig, BioGptConfig, BlenderbotConfig, BlenderbotSmallConfig, BlipConfig, Blip2Config, BloomConfig, BridgeTowerConfig, CamembertConfig, CanineConfig, ChineseCLIPConfig, ClapConfig, CLIPConfig, CLIPSegConfig, CodeGenConfig, ConvBertConfig, CpmAntConfig, CTRLConfig, Data2VecTextConfig, DebertaConfig, DebertaV2Config, DistilBertConfig, DPRConfig, ElectraConfig, ErnieConfig, ErnieMConfig, EsmConfig, FlaubertConfig, FNetConfig, FSMTConfig, FunnelConfig, GitConfig, GPT2Config, GPT2Config, GPTBigCodeConfig, GPTNeoConfig, GPTNeoXConfig, GPTNeoXJapaneseConfig, GPTJConfig, GPTSanJapaneseConfig, GroupViTConfig, HubertConfig, IBertConfig, JukeboxConfig, LayoutLMConfig, LayoutLMv2Config, LayoutLMv3Config, LEDConfig, LiltConfig, LlamaConfig, LongformerConfig, LongT5Config, LukeConfig, LxmertConfig, M2M100Config, MarianConfig, MBartConfig, MegaConfig, MegatronBertConfig, MgpstrConfig, MobileBertConfig, MPNetConfig, MT5Config, MvpConfig, NezhaConfig, NllbMoeConfig, NystromformerConfig, OneFormerConfig, OpenAIGPTConfig, OPTConfig, OwlViTConfig, PegasusConfig, PegasusXConfig, PerceiverConfig, Pix2StructConfig, PLBartConfig, ProphetNetConfig, QDQBertConfig, RagConfig, RealmConfig, ReformerConfig, RemBertConfig, RetriBertConfig, RobertaConfig, RobertaPreLayerNormConfig, RoCBertConfig, RoFormerConfig, RwkvConfig, Speech2TextConfig, Speech2Text2Config, SpeechT5Config, SplinterConfig, SqueezeBertConfig, SwitchTransformersConfig, T5Config, TapasConfig, TransfoXLConfig, ViltConfig, VisualBertConfig, Wav2Vec2Config, Wav2Vec2ConformerConfig, WhisperConfig, XCLIPConfig, XGLMConfig, XLMConfig, XLMProphetNetConfig, XLMRobertaConfig, XLMRobertaXLConfig, XLNetConfig, XmodConfig, YosoConfig.

[Jeffrey G.]

对transformers版本无要求，4.30.2可运行。但这个看起来好像不能复现，可能是因为huggingface的连接不稳定。您现在还有这个问题吗，如果有，可否提供更多细节

[Gu-Penghui]

确实是huggingface不太稳定的原因，还是下载到本地应用最好