(omni) C:\OmniParser\omnitool\omniparserserver>python -m omniparserserver
[2025-03-23 20:48:56,363] [ WARNING] easyocr.py:80 - Neither CUDA nor MPS are available - defaulting to CPU. Note: This module is much faster with a GPU.
Traceback (most recent call last):
File "", line 198, in _run_module_as_main
File "", line 88, in _run_code
File "C:\OmniParser\omnitool\omniparserserver\omniparserserver.py", line 32, in
omniparser = Omniparser(config)
^^^^^^^^^^^^^^^^^^
File "C:\OmniParser\util\omniparser.py", line 13, in init
self.caption_model_processor = get_caption_model_processor(model_name=config['caption_model_name'], model_name_or_path=config['caption_model_path'], device=device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\OmniParser\util\utils.py", line 65, in get_caption_model_processor
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, torch_dtype=torch.float32, trust_remote_code=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AI\envs\omni\Lib\site-packages\transformers\models\auto\auto_factory.py", line 576, in from_pretrained
raise ValueError(
ValueError: Unrecognized configuration class <class 'transformers_modules.microsoft.Florence-2-base-ft.9803f52844ec1ae5df004e6089262e9a23e527fd.configuration_florence2.Florence2LanguageConfig'> for this kind of AutoModel: AutoModelForCausalLM.
Model type should be one of AriaTextConfig, BambaConfig, BartConfig, BertConfig, BertGenerationConfig, BigBirdConfig, BigBirdPegasusConfig, BioGptConfig, BlenderbotConfig, BlenderbotSmallConfig, BloomConfig, CamembertConfig, LlamaConfig, CodeGenConfig, CohereConfig, Cohere2Config, CpmAntConfig, CTRLConfig, Data2VecTextConfig, DbrxConfig, DiffLlamaConfig, ElectraConfig, Emu3Config, ErnieConfig, FalconConfig, FalconMambaConfig, FuyuConfig, GemmaConfig, Gemma2Config, Gemma3Config, Gemma3TextConfig, GitConfig, GlmConfig, GotOcr2Config, GPT2Config, GPT2Config, GPTBigCodeConfig, GPTNeoConfig, GPTNeoXConfig, GPTNeoXJapaneseConfig, GPTJConfig, GraniteConfig, GraniteMoeConfig, GraniteMoeSharedConfig, HeliumConfig, JambaConfig, JetMoeConfig, LlamaConfig, MambaConfig, Mamba2Config, MarianConfig, MBartConfig, MegaConfig, MegatronBertConfig, MistralConfig, MixtralConfig, MllamaConfig, MoshiConfig, MptConfig, MusicgenConfig, MusicgenMelodyConfig, MvpConfig, NemotronConfig, OlmoConfig, Olmo2Config, OlmoeConfig, OpenLlamaConfig, OpenAIGPTConfig, OPTConfig, PegasusConfig, PersimmonConfig, PhiConfig, Phi3Config, PhimoeConfig, PLBartConfig, ProphetNetConfig, QDQBertConfig, Qwen2Config, Qwen2MoeConfig, RecurrentGemmaConfig, ReformerConfig, RemBertConfig, RobertaConfig, RobertaPreLayerNormConfig, RoCBertConfig, RoFormerConfig, RwkvConfig, Speech2Text2Config, StableLmConfig, Starcoder2Config, TransfoXLConfig, TrOCRConfig, WhisperConfig, XGLMConfig, XLMConfig, XLMProphetNetConfig, XLMRobertaConfig, XLMRobertaXLConfig, XLNetConfig, XmodConfig, ZambaConfig, Zamba2Config.
how to solve this problem?
Same here, and after quick search I found other github projects having the same issue - it's coming from an incompatibility in Florence2 and transformers (which just released a new version a few days ago). If you roll back to version 4.49.0 of transformers it should resolve the issue:
python -m pip install --upgrade transformers==4.49.0
microsoft
