MiniCPM-V
MiniCPM-V copied to clipboard
Published
3 months ago
•
OpenBMB
OpenBMB
[BUG] <title>使用官方示例代码报错
是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?
- [x] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions
该问题是否在FAQ中有解答？ | Is there an existing answer for this in FAQ?
- [x] 我已经搜索过FAQ | I have searched FAQ
当前行为 | Current Behavior
运行官方示例代码报错了
## The 3d-resampler compresses multiple frames into 64 tokens by introducing temporal_ids.
# To achieve this, you need to organize your video data into two corresponding sequences:
# frames: List[Image]
# temporal_ids: List[List[Int]].
import torch
from PIL import Image
from transformers import AutoModel, AutoTokenizer
from decord import VideoReader, cpu # pip install decord
from scipy.spatial import cKDTree
import numpy as np
import math
model = AutoModel.from_pretrained('openbmb/MiniCPM-V-4_5', trust_remote_code=True, # or openbmb/MiniCPM-o-2_6
attn_implementation='sdpa', torch_dtype=torch.bfloat16) # sdpa or flash_attention_2, no eager
model = model.eval().cuda()
tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-V-4_5', trust_remote_code=True) # or openbmb/MiniCPM-o-2_6
MAX_NUM_FRAMES=180 # Indicates the maximum number of frames received after the videos are packed. The actual maximum number of valid frames is MAX_NUM_FRAMES * MAX_NUM_PACKING.
MAX_NUM_PACKING=3 # indicates the maximum packing number of video frames. valid range: 1-6
TIME_SCALE = 0.1
错误信息如下
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Cell In[5], line 1
----> 1 tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-V-4_5', trust_remote_code=True) # or openbmb/MiniCPM-o-2_6
File /usr/local/lib/python3.12/dist-packages/transformers/models/auto/tokenization_auto.py:1154, in AutoTokenizer.from_pretrained(cls, pretrained_model_name_or_path, *inputs, **kwargs)
1148 else:
1149 raise ValueError(
1150 "This tokenizer cannot be instantiated. Please make sure you have `sentencepiece` installed "
1151 "in order to use this tokenizer."
1152 )
-> 1154 raise ValueError(
1155 f"Unrecognized configuration class {config.__class__} to build an AutoTokenizer.\n"
1156 f"Model type should be one of {', '.join(c.__name__ for c in TOKENIZER_MAPPING)}."
1157 )
ValueError: Unrecognized configuration class <class 'transformers_modules.openbmb.MiniCPM-V-4_5.bee21bde00e2f93d54212fb1d3bbdda77898de4c.configuration_minicpm.MiniCPMVConfig'> to build an AutoTokenizer.
Model type should be one of Aimv2Config, AlbertConfig, AlignConfig, ArceeConfig, AriaConfig, AyaVisionConfig, BarkConfig, BartConfig, BertConfig, BertGenerationConfig, BigBirdConfig, BigBirdPegasusConfig, BioGptConfig, BitNetConfig, BlenderbotConfig, BlenderbotSmallConfig, BlipConfig, Blip2Config, BloomConfig, BridgeTowerConfig, BrosConfig, CamembertConfig, CanineConfig, ChameleonConfig, ChineseCLIPConfig, ClapConfig, CLIPConfig, CLIPSegConfig, ClvpConfig, LlamaConfig, CodeGenConfig, CohereConfig, Cohere2Config, ColPaliConfig, ColQwen2Config, ConvBertConfig, CpmAntConfig, CTRLConfig, Data2VecAudioConfig, Data2VecTextConfig, DbrxConfig, DebertaConfig, DebertaV2Config, DeepseekV2Config, DeepseekV3Config, DeepseekVLConfig, DeepseekVLHybridConfig, DiaConfig, DiffLlamaConfig, DistilBertConfig, DPRConfig, ElectraConfig, Emu3Config, ErnieConfig, Ernie4_5Config, Ernie4_5_MoeConfig, ErnieMConfig, EsmConfig, Exaone4Config, FalconConfig, FalconMambaConfig, FastSpeech2ConformerConfig, FlaubertConfig, FNetConfig, FSMTConfig, FunnelConfig, GemmaConfig, Gemma2Config, Gemma3Config, Gemma3TextConfig, Gemma3nConfig, Gemma3nTextConfig, GitConfig, GlmConfig, Glm4Config, Glm4MoeConfig, Glm4vConfig, Glm4vMoeConfig, GPT2Config, GPT2Config, GPTBigCodeConfig, GPTNeoConfig, GPTNeoXConfig, GPTNeoXJapaneseConfig, GptOssConfig, GPTJConfig, GPTSanJapaneseConfig, GraniteConfig, GraniteMoeConfig, GraniteMoeHybridConfig, GraniteMoeSharedConfig, GroundingDinoConfig, GroupViTConfig, HeliumConfig, HubertConfig, IBertConfig, IdeficsConfig, Idefics2Config, Idefics3Config, InstructBlipConfig, InstructBlipVideoConfig, InternVLConfig, JambaConfig, JanusConfig, JetMoeConfig, JukeboxConfig, Kosmos2Config, Kosmos2_5Config, LayoutLMConfig, LayoutLMv2Config, LayoutLMv3Config, LEDConfig, LiltConfig, LlamaConfig, Llama4Config, Llama4TextConfig, LlavaConfig, LlavaNextConfig, LlavaNextVideoConfig, LlavaOnevisionConfig, LongformerConfig, LongT5Config, LukeConfig, LxmertConfig, M2M100Config, MambaConfig, Mamba2Config, MarianConfig, MBartConfig, MegaConfig, MegatronBertConfig, MetaClip2Config, MgpstrConfig, MiniMaxConfig, MistralConfig, MixtralConfig, MllamaConfig, MMGroundingDinoConfig, MobileBertConfig, ModernBertConfig, MoonshineConfig, MoshiConfig, MPNetConfig, MptConfig, MraConfig, MT5Config, MusicgenConfig, MusicgenMelodyConfig, MvpConfig, NemotronConfig, NezhaConfig, NllbMoeConfig, NystromformerConfig, OlmoConfig, Olmo2Config, OlmoeConfig, OmDetTurboConfig, OneFormerConfig, OpenAIGPTConfig, OPTConfig, Owlv2Config, OwlViTConfig, PaliGemmaConfig, PegasusConfig, PegasusXConfig, PerceiverConfig, PersimmonConfig, PhiConfig, Phi3Config, PhimoeConfig, Pix2StructConfig, PixtralVisionConfig, PLBartConfig, ProphetNetConfig, QDQBertConfig, Qwen2Config, Qwen2_5OmniConfig, Qwen2_5_VLConfig, Qwen2AudioConfig, Qwen2MoeConfig, Qwen2VLConfig, Qwen3Config, Qwen3MoeConfig, RagConfig, RealmConfig, RecurrentGemmaConfig, ReformerConfig, RemBertConfig, RetriBertConfig, RobertaConfig, RobertaPreLayerNormConfig, RoCBertConfig, RoFormerConfig, RwkvConfig, SeamlessM4TConfig, SeamlessM4Tv2Config, ShieldGemma2Config, SiglipConfig, Siglip2Config, SmolLM3Config, Speech2TextConfig, Speech2Text2Config, SpeechT5Config, SplinterConfig, SqueezeBertConfig, StableLmConfig, Starcoder2Config, SwitchTransformersConfig, T5Config, T5GemmaConfig, TapasConfig, TransfoXLConfig, TvpConfig, UdopConfig, UMT5Config, VideoLlavaConfig, ViltConfig, VipLlavaConfig, VisualBertConfig, VitsConfig, VoxtralConfig, Wav2Vec2Config, Wav2Vec2BertConfig, Wav2Vec2ConformerConfig, WhisperConfig, XCLIPConfig, XGLMConfig, XLMConfig, XLMProphetNetConfig, XLMRobertaConfig, XLMRobertaXLConfig, XLNetConfig, xLSTMConfig, XmodConfig, YosoConfig, ZambaConfig, Zamba2Config.
期望行为 | Expected Behavior
No response
复现方法 | Steps To Reproduce
No response
运行环境 | Environment
- OS:
- Python:
- Transformers:
- PyTorch:
- CUDA (`python -c 'import torch; print(torch.version.cuda)'`):
备注 | Anything else?
No response
@lyy1988323-ctrl 收到您的issue，您的报错感觉是因为transformers版本略低，可以发一下transformers版本么，以及可以升级再试下。
@lyy1988323-ctrl 收到您的issue，您的报错感觉是因为transformers版本略低，可以发一下transformers版本么，以及可以升级再试下。 transformers=4.55.0和4.56都试过了，都是同样的报错
