deepseek-ai/DeepSeek-R1

Fork 0

mirror of https://github.com/deepseek-ai/DeepSeek-R1.git synced 2026-11-05 00:47:42 +00:00

[GH-ISSUE #28] deepseek-r1:32b or 14b almost cannot work in roo cline, because it never calls the tools leading to continuous errors #27

New issue

Closed

opened 2026-10-26 21:11:11 +00:00 by bsakaguchi · 7 comments

bsakaguchi commented

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

Owner

Originally created by @DoiiarX on GitHub (Jan 21, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/28

deepseek-r1:32b or 14b almost cannot work in roo cline, because it never calls the tools leading to continuous errors

Originally created by @DoiiarX on GitHub (Jan 21, 2025). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/28 deepseek-r1:32b or 14b almost cannot work in roo cline, because it never calls the tools leading to continuous errors

bsakaguchi

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

closed this issue
added the
stale

closed-as-stale
labels

bsakaguchi commented

2026-10-26 21:11:13 +00:00

Author

Owner

@LYouC commented on GitHub (Jan 22, 2025):

I also encountered this issue, which might be a problem with the model's capability. I once called qwen2-coder-32b, and it worked fine in roocline. However, deepseek-r1:32b would report an error after multiple repeated invalid conversations.

@LYouC commented on GitHub (Jan 22, 2025): I also encountered this issue, which might be a problem with the model's capability. I once called qwen2-coder-32b, and it worked fine in roocline. However, deepseek-r1:32b would report an error after multiple repeated invalid conversations.

bsakaguchi commented

2026-10-26 21:11:13 +00:00

Author

Owner

@leobarcellos commented on GitHub (Jan 22, 2025):

I could not make it work even with the deepseek-r1:70b

@leobarcellos commented on GitHub (Jan 22, 2025): I could not make it work even with the deepseek-r1:70b

bsakaguchi commented

2026-10-26 21:11:13 +00:00

Author

Owner

@jp-gorman commented on GitHub (Jan 22, 2025):

I have the same issue using cline and the R1-32B model locally on ollama using ollama published R1 model.

@jp-gorman commented on GitHub (Jan 22, 2025): I have the same issue using cline and the R1-32B model locally on ollama using ollama published R1 model.

bsakaguchi commented

2026-10-26 21:11:14 +00:00

Author

Owner

@Zodaztream commented on GitHub (Jan 22, 2025):

For me the issue was context length, the default context length is around 4K for Ollama. You can fix this by creating a Modelfile with the following:

FROM deepseek-r1:14b
PARAMETER num_ctx 32768

and then create a model from this with a unique name using ollama. Choose this model in cline and it should start working.

You can also use LM studio which allows to increase context length by holding alt over the model before loading it.

These two approaches will make it work.

@Zodaztream commented on GitHub (Jan 22, 2025): For me the issue was context length, the default context length is around 4K for Ollama. You can fix this by creating a Modelfile with the following: > FROM deepseek-r1:14b > PARAMETER num_ctx 32768 and then create a model from this with a unique name using ollama. Choose this model in cline and it should start working. You can also use LM studio which allows to increase context length by holding alt over the model before loading it. These two approaches will make it work.

bsakaguchi commented

2026-10-26 21:11:15 +00:00

Author

Owner

@jwadow commented on GitHub (Jan 22, 2025):

For me the issue was context length, the default context length is around 4K for Ollama. You can fix this by creating a Modelfile with the following:

FROM deepseek-r1:14b
PARAMETER num_ctx 32768

and then create a model from this with a unique name using ollama. Choose this model in cline and it should start working.

Yes, thank you, it worked and became much better. For 14B I set num_ctx 25000 and it is able to complete the simple task, albeit after a long time.
7B and especially 1.5B with 32768 are not able to complete the simple task.

R1 models seem to not understand that they need to work with an open active file and replace 1 variable there (in "Code" mode).

But there are still certain technical shortcomings in roo cline:

The model constantly uses visible tags like <tool_use> and <ask_ollowup_question>.
For some reason, the beginning of the answer is very long. I think the problem is that this is a <think> block that is invisible to the user? It would be nice to add a pop-up inscription "Thinking", if so.

Oh, I noticed that this is not a repo of roo cline, but of the creator of the model.

@jwadow commented on GitHub (Jan 22, 2025): > For me the issue was context length, the default context length is around 4K for Ollama. You can fix this by creating a Modelfile with the following: > > > FROM deepseek-r1:14b > > PARAMETER num_ctx 32768 > > and then create a model from this with a unique name using ollama. Choose this model in cline and it should start working. Yes, thank you, it worked and became much better. For 14B I set num_ctx 25000 and it is able to complete the simple task, albeit after a long time. 7B and especially 1.5B with 32768 are not able to complete the simple task. R1 models seem to not understand that they need to work with an open active file and replace 1 variable there (in "Code" mode). But there are still certain technical shortcomings in roo cline: 1) The model constantly uses visible tags like <tool_use> and <ask_ollowup_question>. 2) For some reason, the beginning of the answer is very long. I think the problem is that this is a `<think>` block that is invisible to the user? It would be nice to add a pop-up inscription "Thinking", if so. Oh, I noticed that this is not a repo of roo cline, but of the creator of the model.

bsakaguchi commented

2026-10-26 21:11:15 +00:00

Author

Owner

@github-actions[bot] commented on GitHub (Feb 22, 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!

@github-actions[bot] commented on GitHub (Feb 22, 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!

bsakaguchi commented

2026-10-26 21:11:16 +00:00

Author

Owner

@github-actions[bot] commented on GitHub (Mar 17, 2025):

false

@github-actions[bot] commented on GitHub (Mar 17, 2025): false