github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #3909] ollama can not run the custom model (finetune on llama3) on M1 max #2422

New Issue
Closed
opened 2026-04-12 12:43:53 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 12:43:53 -05:00
Owner
Copy Link

Originally created by @TobyYang7 on GitHub (Apr 25, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3909

What is the issue?

❯ ollama run InsuranceGPT "What is your favourite condiment?"
Error: llama runner process no longer running: -1 error:check_tensor_dims: tensor 'blk.0.attn_k.weight' has wrong shape; expected 4096, 4096, got 4096, 1024, 1, 1

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

No response

Originally created by @TobyYang7 on GitHub (Apr 25, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3909 ### What is the issue? ❯ ollama run InsuranceGPT "What is your favourite condiment?" Error: llama runner process no longer running: -1 error:check_tensor_dims: tensor 'blk.0.attn_k.weight' has wrong shape; expected 4096, 4096, got 4096, 1024, 1, 1 ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 12:43:53 -05:00
GiteaMirror commented 2026-04-12 12:43:54 -05:00
Author
Owner
Copy Link

@TobyYang7 commented on GitHub (Apr 25, 2024):

❯ ollama create InsuranceGPT -f Modelfile
transferring model data
creating model layer
creating template layer
using already created layer sha256:9ff789dfa477f6c77a5e6a8e4be66df28d824c18cf84e24d1b14aac2d067e950
writing layer sha256:26fc224b78fce98e2c791de92ec7687171a7b46236f34faa64227cf9c2cfa4ac
writing layer sha256:8854ff53cb2acccb83c87e946efc533a82b038d6d243caddd7ed0ba2e766ef84
writing manifest
success
❯ ollama run InsuranceGPT "What is your favourite condiment?"
Error: llama runner process no longer running: -1 error:check_tensor_dims: tensor 'blk.0.attn_k.weight' has wrong shape; expected 4096, 4096, got 4096, 1024, 1, 1

<!-- gh-comment-id:2077102472 --> @TobyYang7 commented on GitHub (Apr 25, 2024): ❯ ollama create InsuranceGPT -f Modelfile transferring model data creating model layer creating template layer using already created layer sha256:9ff789dfa477f6c77a5e6a8e4be66df28d824c18cf84e24d1b14aac2d067e950 writing layer sha256:26fc224b78fce98e2c791de92ec7687171a7b46236f34faa64227cf9c2cfa4ac writing layer sha256:8854ff53cb2acccb83c87e946efc533a82b038d6d243caddd7ed0ba2e766ef84 writing manifest success ❯ ollama run InsuranceGPT "What is your favourite condiment?" Error: llama runner process no longer running: -1 error:check_tensor_dims: tensor 'blk.0.attn_k.weight' has wrong shape; expected 4096, 4096, got 4096, 1024, 1, 1
GiteaMirror commented 2026-04-12 12:43:55 -05:00
Author
Owner
Copy Link

@Shrijeeth commented on GitHub (Apr 28, 2024):

Facing same issue for code-gemma-7B gguf model
Error: llama runner process no longer running: -1 error:check_tensor_dims: tensor 'blk.0.attn_q.weight' has wrong shape; expected 3072, 3072, got 3072, 4096, 1, 1

<!-- gh-comment-id:2081593930 --> @Shrijeeth commented on GitHub (Apr 28, 2024): Facing same issue for code-gemma-7B gguf model `Error: llama runner process no longer running: -1 error:check_tensor_dims: tensor 'blk.0.attn_q.weight' has wrong shape; expected 3072, 3072, got 3072, 4096, 1, 1`
GiteaMirror commented 2026-04-12 12:43:56 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jul 11, 2024):

@TobyYang7 or @Shrijeeth sorry for the slow response for the issue. Do either of you have the gguf file / modelfile that exhibits the problem? I'm guessing it's an issue w/ an improperly converted gguf file.

<!-- gh-comment-id:2221941915 --> @pdevine commented on GitHub (Jul 11, 2024): @TobyYang7 or @Shrijeeth sorry for the slow response for the issue. Do either of you have the gguf file / modelfile that exhibits the problem? I'm guessing it's an issue w/ an improperly converted gguf file.
GiteaMirror commented 2026-04-12 12:43:57 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Oct 23, 2024):

I'm going to go ahead and close the issue.

<!-- gh-comment-id:2432997902 --> @pdevine commented on GitHub (Oct 23, 2024): I'm going to go ahead and close the issue.
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#2422
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?