github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10602] Error converting from safetensors" error="unsupported architecture "Qwen3ForCausalLM" #53486

New Issue
Closed
opened 2026-04-29 03:22:42 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-29 03:22:42 -05:00
Owner
Copy Link

Originally created by @ArchCangyuan on GitHub (May 7, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10602

What is the issue?

When importing safetensors of Qwen3 model, the log reports msg="error converting from safetensors" error="unsupported architecture "Qwen3ForCausalLM"".

Relevant log output

level=ERROR source=create.go:162 msg="error converting from safetensors" error="unsupported architecture \"Qwen3ForCausalLM\""

OS

No response

GPU

No response

CPU

No response

Ollama version

0.6.8

Originally created by @ArchCangyuan on GitHub (May 7, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10602 ### What is the issue? When importing safetensors of Qwen3 model, the log reports msg="error converting from safetensors" error="unsupported architecture \"Qwen3ForCausalLM\"". ### Relevant log output ```shell level=ERROR source=create.go:162 msg="error converting from safetensors" error="unsupported architecture \"Qwen3ForCausalLM\"" ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version 0.6.8
GiteaMirror added the bug label 2026-04-29 03:22:42 -05:00
GiteaMirror commented 2026-04-29 03:22:48 -05:00
Author
Owner
Copy Link

@c5g2 commented on GitHub (May 7, 2025):

I had the same problem using 1.7B

<!-- gh-comment-id:2857603717 --> @c5g2 commented on GitHub (May 7, 2025): I had the same problem using 1.7B
GiteaMirror commented 2026-04-29 03:22:53 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 7, 2025):

The ollama import function only supports a subset of architectures. For un-supported models, you can use llama.cpp to convert to GGUF and then import that.

<!-- gh-comment-id:2857825351 --> @rick-github commented on GitHub (May 7, 2025): The ollama import function only supports a subset of architectures. For un-supported models, you can use [llama.cpp](https://github.com/ggml-org/llama.cpp/blob/master/convert_hf_to_gguf_update.py) to convert to GGUF and then import that.
GiteaMirror commented 2026-04-29 03:22:54 -05:00
Author
Owner
Copy Link

@ArchCangyuan commented on GitHub (May 7, 2025):

The ollama import function only supports a subset of architectures. For un-supported models, you can use llama.cpp to convert to GGUF and then import that.

I also tried use HF to GGUF tool from llama.cpp project. The import process seems fine. But I got "panic: interface conversion: interface {} is nil, not *ggml.array[string]" when I calling the imported model.

<!-- gh-comment-id:2858341715 --> @ArchCangyuan commented on GitHub (May 7, 2025): > The ollama import function only supports a subset of architectures. For un-supported models, you can use [llama.cpp](https://github.com/ggml-org/llama.cpp/blob/master/convert_hf_to_gguf_update.py) to convert to GGUF and then import that. I also tried use HF to GGUF tool from llama.cpp project. The import process seems fine. But I got "panic: interface conversion: interface {} is nil, not *ggml.array[string]" when I calling the imported model.
GiteaMirror commented 2026-04-29 03:22:55 -05:00
Author
Owner
Copy Link

@galoisgroupcn commented on GitHub (May 10, 2025):

@ArchCangyuan @c5g2 @rick-github here's our fix. let us know if you have any feedback. https://github.com/ollama/ollama/pull/10644

<!-- gh-comment-id:2868409614 --> @galoisgroupcn commented on GitHub (May 10, 2025): @ArchCangyuan @c5g2 @rick-github here's our fix. let us know if you have any feedback. https://github.com/ollama/ollama/pull/10644
GiteaMirror commented 2026-04-29 03:22:56 -05:00
Author
Owner
Copy Link

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

#9984 for the panic.

<!-- gh-comment-id:2919759293 --> @rick-github commented on GitHub (May 29, 2025): #9984 for the panic.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#53486
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?