OpenELM causing transformers Exception

[Wladastic]

Describe the bug

For some reason tranformers is throwing an Exception when loading OpenELM from Apple although they state in their own README to use transformers. I think the config is missing in text-generation-webui

Is there an existing issue for this?

• [X] I have searched the existing issues

Reproduction

Download and try to load OpenELM-1.1B or 3B using transformers.

Screenshot

No response

Logs

File "/home/user/text-generation-webui/installer_files/env/lib/python3.11/site-packages/transformers/models/auto/tokenization_auto.py", line 890, in from_pretrained

raise ValueError(
ValueError: Unrecognized configuration class <class 'transformers_modules.apple_OpenELM-1_1B-Instruct.configuration_openelm.OpenELMConfig'> to build an AutoTokenizer.

Model type should be one of AlbertConfig, AlignConfig, BarkConfig, BartConfig, BertConfig, BertGenerationConfig, BigBirdConfig, BigBirdPegasusConfig, BioGptConfig, BlenderbotConfig, BlenderbotSmallConfig, BlipConfig, Blip2Config, BloomConfig, BridgeTowerConfig, BrosConfig, CamembertConfig, CanineConfig, ChineseCLIPConfig, ClapConfig, CLIPConfig, CLIPSegConfig, ClvpConfig, LlamaConfig, CodeGenConfig, CohereConfig, ConvBertConfig, CpmAntConfig, CTRLConfig, Data2VecAudioConfig, Data2VecTextConfig, DbrxConfig, DebertaConfig, DebertaV2Config, DistilBertConfig, DPRConfig, ElectraConfig, ErnieConfig, ErnieMConfig, EsmConfig, FalconConfig, FastSpeech2ConformerConfig, FlaubertConfig, FNetConfig, FSMTConfig, FunnelConfig, GemmaConfig, GitConfig, GPT2Config, GPT2Config, GPTBigCodeConfig, GPTNeoConfig, GPTNeoXConfig, GPTNeoXJapaneseConfig, GPTJConfig, GPTSanJapaneseConfig, GroundingDinoConfig, GroupViTConfig, HubertConfig, IBertConfig, IdeficsConfig, Idefics2Config, InstructBlipConfig, JambaConfig, JukeboxConfig, Kosmos2Config, LayoutLMConfig, LayoutLMv2Config, LayoutLMv3Config, LEDConfig, LiltConfig, LlamaConfig, LlavaConfig, LlavaNextConfig, LongformerConfig, LongT5Config, LukeConfig, LxmertConfig, M2M100Config, MambaConfig, MarianConfig, MBartConfig, MegaConfig, MegatronBertConfig, MgpstrConfig, MistralConfig, MixtralConfig, MobileBertConfig, MPNetConfig, MptConfig, MraConfig, MT5Config, MusicgenConfig, MusicgenMelodyConfig, MvpConfig, NezhaConfig, NllbMoeConfig, NystromformerConfig, OlmoConfig, OneFormerConfig, OpenAIGPTConfig, OPTConfig, Owlv2Config, OwlViTConfig, PegasusConfig, PegasusXConfig, PerceiverConfig, PersimmonConfig, PhiConfig, Pix2StructConfig, PLBartConfig, ProphetNetConfig, QDQBertConfig, Qwen2Config, Qwen2MoeConfig, RagConfig, RealmConfig, RecurrentGemmaConfig, ReformerConfig, RemBertConfig, RetriBertConfig, RobertaConfig, RobertaPreLayerNormConfig, RoCBertConfig, RoFormerConfig, RwkvConfig, SeamlessM4TConfig, SeamlessM4Tv2Config, SiglipConfig, Speech2TextConfig, Speech2Text2Config, SpeechT5Config, SplinterConfig, SqueezeBertConfig, StableLmConfig, Starcoder2Config, SwitchTransformersConfig, T5Config, TapasConfig, TransfoXLConfig, TvpConfig, UdopConfig, UMT5Config, ViltConfig, VipLlavaConfig, VisualBertConfig, VitsConfig, Wav2Vec2Config, Wav2Vec2BertConfig, Wav2Vec2ConformerConfig, WhisperConfig, XCLIPConfig, XGLMConfig, XLMConfig, XLMProphetNetConfig, XLMRobertaConfig, XLMRobertaXLConfig, XLNetConfig, XmodConfig, YosoConfig.

System Info

WSL2 Ubuntu on Windows 11

[kxbin]

I have the same problem

[anud18]

The OpenELM model in the Hugging Face repository doesn't include a tokenizer. An alternative solution is to place a compatible tokenizer in the OpenELM model directory. For example, I placed the Llama-2-7b-hf (official example tokenizer) in the model directory. This resolved the transformers exception.

System Info

WSL2 Ubuntu on Windows 11