[GH-ISSUE #10904] Error converting from safetensors => Error: unsupported architecture "DeepseekV3ForCausalLM" #32929

Closed
opened 2026-04-22 14:53:28 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @seanlinmt on GitHub (May 29, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10904

What is the issue?

When importing safetensors of DeepSeek-R1-0528 model, I'm getting the following error:

Error: unsupported architecture "DeepseekV3ForCausalLM"

Relevant log output


OS

Linux

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @seanlinmt on GitHub (May 29, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10904 ### What is the issue? When importing safetensors of DeepSeek-R1-0528 model, I'm getting the following error: Error: unsupported architecture "DeepseekV3ForCausalLM" ### Relevant log output ```shell ``` ### OS Linux ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-22 14:53:28 -05:00
Author
Owner

@rick-github commented on GitHub (May 29, 2025):

DeepseekV3ForCausalLM is currently not a supported architecture for importing via ollama. Try the convert_hf_to_gguf.py script from llama.cpp.

<!-- gh-comment-id:2920691314 --> @rick-github commented on GitHub (May 29, 2025): DeepseekV3ForCausalLM is currently not a supported architecture for importing via ollama. Try the [`convert_hf_to_gguf.py`](https://github.com/ggml-org/llama.cpp/blob/e83ba3e460651b20a594e9f2f0f0bffb998d3ce1/convert_hf_to_gguf.py#L5137) script from llama.cpp.
Author
Owner

@seanlinmt commented on GitHub (May 29, 2025):

I see support for DeepSeekR1-0528 has been added in v0.9.0-rc0. Closing ticket.

<!-- gh-comment-id:2920712529 --> @seanlinmt commented on GitHub (May 29, 2025): I see support for DeepSeekR1-0528 has been added in v0.9.0-rc0. Closing ticket.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#32929