[GH-ISSUE #105] Large number of warning messages for: "deepseek-ai/deepseek-vl2-tiny" #86

New issue

Open

opened 2026-10-26 21:11:42 +00:00 by bsakaguchi · 2 comments

bsakaguchi commented

2026-10-26 21:11:42 +00:00

Owner

Originally created by @ukaprch on GitHub (Feb 27, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-VL2/issues/105

Running Windows 10
Python 3.12.5 with latest libraries installed

The model loads OK, but a large number of warning messages has me wondering if you folks intend on supporting this model for future diffusers github updates.

You are using the default legacy behaviour of the <class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>. This is expected, and simply means that the legacy (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set legacy=False. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565 - if you loaded a llama tokenizer from a GGUF file you can ignore this message.
Some kwargs in processor config are unused and will not have any effect: candidate_resolutions, image_token, image_std, pad_token, sft_format, add_special_token, normalize, mask_prompt, ignore_id, downsample_ratio, patch_size, image_mean.
Add pad token = ['<｜▁pad▁｜>'] to the tokenizer
<｜▁pad▁｜>:2
Add image token = [''] to the tokenizer
:128815
Add grounding-related tokens = ['<|ref|>', '<|/ref|>', '<|det|>', '<|/det|>', '<|grounding|>'] to the tokenizer with input_ids
<|ref|>:128816
<|/ref|>:128817
<|det|>:128818
<|/det|>:128819
<|grounding|>:128820
Add chat tokens = ['<|User|>', '<|Assistant|>'] to the tokenizer with input_ids
<|User|>:128821
<|Assistant|>:128822

DeepseekVLV2ForCausalLM has generative capabilities, as prepare_inputs_for_generation is explicitly overwritten. However, it doesn't directly inherit from GenerationMixin. From 👉v4.50👈 onwards, PreTrainedModel will NOT inherit from GenerationMixin, and this model will lose the ability to call generate and other related functions.

If you're using trust_remote_code=True, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
If you are the owner of the model architecture code, please modify your model class such that it inherits from GenerationMixin (after PreTrainedModel, otherwise you'll get an exception).
If you are not the owner of the model architecture class, please contact the model code owner to update it.
DeepseekV2ForCausalLM has generative capabilities, as prepare_inputs_for_generation is explicitly overwritten. However, it doesn't directly inherit from GenerationMixin. From 👉v4.50👈 onwards, PreTrainedModel will NOT inherit from GenerationMixin, and this model will lose the ability to call generate and other related functions.
If you're using trust_remote_code=True, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
If you are the owner of the model architecture code, please modify your model class such that it inherits from GenerationMixin (after PreTrainedModel, otherwise you'll get an exception).
If you are not the owner of the model architecture class, please contact the model code owner to update it.

Please advise.

Originally created by @ukaprch on GitHub (Feb 27, 2025). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-VL2/issues/105 Running Windows 10 Python 3.12.5 with latest libraries installed The model loads OK, but a large number of warning messages has me wondering if you folks intend on supporting this model for future diffusers github updates. You are using the default legacy behaviour of the <class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565 - if you loaded a llama tokenizer from a GGUF file you can ignore this message. Some kwargs in processor config are unused and will not have any effect: candidate_resolutions, image_token, image_std, pad_token, sft_format, add_special_token, normalize, mask_prompt, ignore_id, downsample_ratio, patch_size, image_mean. Add pad token = ['<｜▁pad▁｜>'] to the tokenizer <｜▁pad▁｜>:2 Add image token = ['<image>'] to the tokenizer <image>:128815 Add grounding-related tokens = ['<|ref|>', '<|/ref|>', '<|det|>', '<|/det|>', '<|grounding|>'] to the tokenizer with input_ids <|ref|>:128816 <|/ref|>:128817 <|det|>:128818 <|/det|>:128819 <|grounding|>:128820 Add chat tokens = ['<|User|>', '<|Assistant|>'] to the tokenizer with input_ids <|User|>:128821 <|Assistant|>:128822 DeepseekVLV2ForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly overwritten. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions. - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception). - If you are not the owner of the model architecture class, please contact the model code owner to update it. DeepseekV2ForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly overwritten. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions. - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception). - If you are not the owner of the model architecture class, please contact the model code owner to update it. Please advise.

bsakaguchi commented

2026-10-26 21:11:43 +00:00

Author

Owner

@MRYUjg commented on GitHub (Mar 12, 2025):

I get this problem,how to solve it ,please?

@MRYUjg commented on GitHub (Mar 12, 2025): I get this problem,how to solve it ,please?

bsakaguchi commented

2026-10-26 21:11:44 +00:00

Author

Owner

@ukaprch commented on GitHub (Mar 12, 2025):

@MRYUjg
It's not really a problem, but a warning message. My question pertains to updating the model for future changes in the /env

@ukaprch commented on GitHub (Mar 12, 2025): @MRYUjg It's not really a problem, but a warning message. My question pertains to updating the model for future changes in the /env

No labels

pull-request

No milestone

No project

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

deepseek-ai/DeepSeek-VL2#86

No description provided.

Rows
Columns