What tokenizer does uform model use ?
I'm trying to quantize the model using GPTQ
after running
from transformers import AutoModelForCausalLM, AutoTokenizer, GPTQConfig
import torch
model_id = "unum-cloud/uform-gen2-qwen-500m"
quantization_config = GPTQConfig(
bits=4,
group_size=128,
dataset="c4",
desc_act=False,
)
tokenizer = AutoTokenizer.from_pretrained(model_id)
quant_model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=quantization_config, device_map='auto')
i got this error :
ValueError: Unrecognized configuration class <class 'transformers_modules.unum-cloud.uform-gen2-qwen-500m.3912572ad204f82a2b0f875d3a1700faaebab719.configuration_uform_gen.VLMConfig'> 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, ConvBertConfig, CpmAntConfig, CTRLConfig, Data2VecAudioConfig, Data2VecTextConfig, DebertaConfig, DebertaV2Config, DistilBertConfig, DPRConfig, ElectraConfig, ErnieConfig, ErnieMConfig, EsmConfig, FalconConfig, FastSpeech2ConformerConfig, FlaubertConfig, FNetConfig, FSMTConfig, FunnelConfig, GemmaConfig, GitConfig, GPT2Config, GPT2Config, GPTBigCodeConfig, GPTNeoConfig, GPTNeoXConfig, GPTNeoXJapaneseConfig, GPTJConfig, GPTSanJapaneseConfig, GroupViTConfig, HubertConfig, IBertConfig, IdeficsConfig, InstructBlipConfig, JukeboxConfig, Kosmos2Config, LayoutLMConfig, LayoutLMv2Config, LayoutLMv3Config, LEDConfig, LiltConfig, LlamaConfig, LlavaConfig, LongformerConfig, LongT5Config, LukeConfig, LxmertConfig, M2M100Config, MarianConfig, MBartConfig, MegaConfig, MegatronBertConfig, MgpstrConfig, MistralConfig, MixtralConfig, MobileBertConfig, MPNetConfig, MptConfig, MraConfig, MT5Config, MusicgenConfig, MvpConfig, NezhaConfig, NllbMoeConfig, NystromformerConfig, OneFormerConfig, OpenAIGPTConfig, OPTConfig, Owlv2Config, OwlViTConfig, PegasusConfig, PegasusXConfig, PerceiverConfig, Persi...
Our model is multimodal, so it doesn't use only text tokenizer, but also image preprocessor.