[GH-ISSUE #363] DeepSeek-R1 model on HuggingFace Hub #285

Closed
opened 2026-10-26 21:18:47 +00:00 by bsakaguchi · 4 comments
Owner

Originally created by @saman-rahbar on GitHub (Feb 10, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/363

Hello everyone,

I wanted to flag a recent change in the DeepSeek-R1 model on HuggingFace Hub (including its distilled version). the chat template in tokenizer_config.json was updated to add a line "\n" at the end. it seems this modification aims to ensure the model begins from the “thinking” process rather than skipping that step entirely.

However, this change has unfortunately disrupted the functionality of the reasoning-parser in vLLM for DeepSeek-R1. I’m not certain who oversees the deepseek_r1 reasoning-parser within vLLM, but I would greatly appreciate any assistance in resolving this issue as soon as possible.

Thank you!

Originally created by @saman-rahbar on GitHub (Feb 10, 2025). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/363 Hello everyone, I wanted to flag a recent change in the DeepSeek-R1 model on HuggingFace Hub (including its distilled version). the chat template in tokenizer_config.json was updated to add a line "<think>\n" at the end. it seems this modification aims to ensure the model begins from the “thinking” process rather than skipping that step entirely. However, this change has unfortunately disrupted the functionality of the reasoning-parser in vLLM for DeepSeek-R1. I’m not certain who oversees the deepseek_r1 reasoning-parser within vLLM, but I would greatly appreciate any assistance in resolving this issue as soon as possible. Thank you!
bsakaguchi 2026-10-26 21:18:47 +00:00
Author
Owner

@ch9hn commented on GitHub (Feb 12, 2025):

We are facing exactly the same issue, related to that issue here: https://github.com/vllm-project/vllm/issues/13125

<!-- gh-comment-id:2654905398 --> @ch9hn commented on GitHub (Feb 12, 2025): We are facing exactly the same issue, related to that issue here: https://github.com/vllm-project/vllm/issues/13125
Author
Owner

@Xavier-Corbier commented on GitHub (Mar 10, 2025):

Do you have an answer to this issue please ?

<!-- gh-comment-id:2710720394 --> @Xavier-Corbier commented on GitHub (Mar 10, 2025): Do you have an answer to this issue please ?
Author
Owner

@github-actions[bot] commented on GitHub (Apr 29, 2025):

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you believe this issue is still relevant, please leave a comment to keep it open. Thank you for your contributions!

<!-- gh-comment-id:2837063652 --> @github-actions[bot] commented on GitHub (Apr 29, 2025): This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you believe this issue is still relevant, please leave a comment to keep it open. Thank you for your contributions!
Author
Owner

@github-actions[bot] commented on GitHub (May 30, 2025):

false

<!-- gh-comment-id:2920855674 --> @github-actions[bot] commented on GitHub (May 30, 2025): false
Sign in to join this conversation.
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-R1#285
No description provided.