deepseek-ai/DeepSeek-VL2
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-VL2.git synced 2026-11-05 01:07:23 +00:00
Code Issues 123 Projects Packages Wiki Activity

[GH-ISSUE #25] Transformers does not recognize this architecture #22

New issue
Closed
opened 2026-10-26 21:10:21 +00:00 by bsakaguchi · 2 comments
bsakaguchi commented 2026-10-26 21:10:21 +00:00
Owner
Copy link

Originally created by @DeadLining on GitHub (Dec 27, 2024).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-VL2/issues/25

The version of Transformers is 4.47.1, but ms-swift raise the following error:

ValueError: The checkpoint you are trying to load has model type deepseek_vl2 but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

ms-swift:
CUDA_VISIBLE_DEVICES=0,1,2,3 \ VIDEO_MAX_PIXELS=50176 \ swift sft \ --model /gpu/nfs/raymodel/deepseek-ai/deepseek-vl2-small \ --train_type lora \ --dataset accident/train.jsonl \ --num_train_epochs 10 \ --per_device_train_batch_size 2 \ --learning_rate 1e-4 \ --lora_rank 8 \ --lora_alpha 32 \ --gradient_accumulation_steps 16 \ --eval_steps 50 \ --save_steps 50 \ --save_total_limit 2 \ --logging_steps 10 \ --target_modules all-linear \ --freeze_llm false \ --freeze_vit false \ --freeze_aligner false

Originally created by @DeadLining on GitHub (Dec 27, 2024). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-VL2/issues/25 The version of Transformers is 4.47.1, but ms-swift raise the following error: `ValueError: The checkpoint you are trying to load has model type `deepseek_vl2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.` ms-swift: `CUDA_VISIBLE_DEVICES=0,1,2,3 \ VIDEO_MAX_PIXELS=50176 \ swift sft \ --model /gpu/nfs/raymodel/deepseek-ai/deepseek-vl2-small \ --train_type lora \ --dataset accident/train.jsonl \ --num_train_epochs 10 \ --per_device_train_batch_size 2 \ --learning_rate 1e-4 \ --lora_rank 8 \ --lora_alpha 32 \ --gradient_accumulation_steps 16 \ --eval_steps 50 \ --save_steps 50 \ --save_total_limit 2 \ --logging_steps 10 \ --target_modules all-linear \ --freeze_llm false \ --freeze_vit false \ --freeze_aligner false `
bsakaguchi commented 2026-10-26 21:10:24 +00:00
Author
Owner
Copy link

@Alane-Henry commented on GitHub (Feb 12, 2025):

Hi, how did you solve this problem?

<!-- gh-comment-id:2652838783 --> @Alane-Henry commented on GitHub (Feb 12, 2025): Hi, how did you solve this problem?
bsakaguchi commented 2026-10-26 21:10:24 +00:00
Author
Owner
Copy link

@VineethKrishnaAvadhanam commented on GitHub (Feb 12, 2025):

Well I am stuck here , What is the Solution ?

<!-- gh-comment-id:2653576177 --> @VineethKrishnaAvadhanam commented on GitHub (Feb 12, 2025): Well I am stuck here , What is the Solution ?
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
No results found.
Labels
Clear labels   
pull-request
Mirrored from GitHub Pull Request

No labels
pull-request
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
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#22
No description provided.