github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #5460] custom model: error loading model: check_tensor_dims: tensor 'blk.0.ffn_norm.weight' not found #3416

New Issue
Closed
opened 2026-04-12 14:03:31 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 14:03:31 -05:00
Owner
Copy Link

Originally created by @finnbusse on GitHub (Jul 3, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5460

What is the issue?

I recently trained a custom AI model using Google Colab with Alpaca and Unsloth. The training process was successful, but when attempting to run the model using Ollama, I encountered an error.

C:\Users\Finn\Downloads>ollama run test2 Error: llama runner process has terminated: exit status 0xc0000409

Building of this AI model was sucessful:

C:\Users\Finn\Downloads>ollama create test2 -f Modelfile transferring model data using existing layer sha256:b9175c65733392c2bf6c90c4a2fc5772b948369ec3269fb7b0b1f2ae24a8ac2c creating new layer sha256:73d81a2944b28d56a86a4bd8980f14085e5ec0e894b80f1932da1010a2411add writing manifest success

Modelfile:
FROM test2.gguf

Before that, I was able to chat with the model within Google Colab.

Server logs:

Device 0: NVIDIA GeForce RTX 3060 Ti, compute capability 8.6, VMM: yes llm_load_tensors: ggml ctx size = 0.39 MiB llama_model_load: error loading model: check_tensor_dims: tensor 'blk.0.ffn_norm.weight' not found llama_load_model_from_file: exception loading model time=2024-07-03T14:34:25.661+02:00 level=INFO source=server.go:594 msg="waiting for server to become available" status="llm server error" time=2024-07-03T14:34:25.921+02:00 level=ERROR source=sched.go:388 msg="error loading llama server" error="llama runner process has terminated: exit status 0xc0000409 " [GIN] 2024/07/03 - 14:34:25 | 500 | 1.1579959s | 127.0.0.1 | POST "/api/chat" time=2024-07-03T14:34:30.949+02:00 level=WARN source=sched.go:575 msg="gpu VRAM usage didn't recover within timeout" seconds=5.0273536 model=C:\Users\Finn\.ollama\models\blobs\sha256-b9175c65733392c2bf6c90c4a2fc5772b948369ec3269fb7b0b1f2ae24a8ac2c time=2024-07-03T14:34:31.199+02:00 level=WARN source=sched.go:575 msg="gpu VRAM usage didn't recover within timeout" seconds=5.2771314 model=C:\Users\Finn\.ollama\models\blobs\sha256-b9175c65733392c2bf6c90c4a2fc5772b948369ec3269fb7b0b1f2ae24a8ac2c time=2024-07-03T14:34:31.451+02:00 level=WARN source=sched.go:575 msg="gpu VRAM usage didn't recover within timeout" seconds=5.5292856 model=C:\Users\Finn\.ollama\models\blobs\sha256-b9175c65733392c2bf6c90c4a2fc5772b948369ec3269fb7b0b1f2ae24a8ac2c

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.1.48

Originally created by @finnbusse on GitHub (Jul 3, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5460 ### What is the issue? I recently trained a custom AI model using Google Colab with Alpaca and Unsloth. The training process was successful, but when attempting to run the model using Ollama, I encountered an error. `C:\Users\Finn\Downloads>ollama run test2 Error: llama runner process has terminated: exit status 0xc0000409` Building of this AI model was sucessful: `C:\Users\Finn\Downloads>ollama create test2 -f Modelfile transferring model data using existing layer sha256:b9175c65733392c2bf6c90c4a2fc5772b948369ec3269fb7b0b1f2ae24a8ac2c creating new layer sha256:73d81a2944b28d56a86a4bd8980f14085e5ec0e894b80f1932da1010a2411add writing manifest success` Modelfile: `FROM test2.gguf` Before that, I was able to chat with the model within Google Colab. Server logs: ` Device 0: NVIDIA GeForce RTX 3060 Ti, compute capability 8.6, VMM: yes llm_load_tensors: ggml ctx size = 0.39 MiB llama_model_load: error loading model: check_tensor_dims: tensor 'blk.0.ffn_norm.weight' not found llama_load_model_from_file: exception loading model time=2024-07-03T14:34:25.661+02:00 level=INFO source=server.go:594 msg="waiting for server to become available" status="llm server error" time=2024-07-03T14:34:25.921+02:00 level=ERROR source=sched.go:388 msg="error loading llama server" error="llama runner process has terminated: exit status 0xc0000409 " [GIN] 2024/07/03 - 14:34:25 | 500 | 1.1579959s | 127.0.0.1 | POST "/api/chat" time=2024-07-03T14:34:30.949+02:00 level=WARN source=sched.go:575 msg="gpu VRAM usage didn't recover within timeout" seconds=5.0273536 model=C:\Users\Finn\.ollama\models\blobs\sha256-b9175c65733392c2bf6c90c4a2fc5772b948369ec3269fb7b0b1f2ae24a8ac2c time=2024-07-03T14:34:31.199+02:00 level=WARN source=sched.go:575 msg="gpu VRAM usage didn't recover within timeout" seconds=5.2771314 model=C:\Users\Finn\.ollama\models\blobs\sha256-b9175c65733392c2bf6c90c4a2fc5772b948369ec3269fb7b0b1f2ae24a8ac2c time=2024-07-03T14:34:31.451+02:00 level=WARN source=sched.go:575 msg="gpu VRAM usage didn't recover within timeout" seconds=5.5292856 model=C:\Users\Finn\.ollama\models\blobs\sha256-b9175c65733392c2bf6c90c4a2fc5772b948369ec3269fb7b0b1f2ae24a8ac2c` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.48
GiteaMirror added the bug label 2026-04-12 14:03:32 -05:00
GiteaMirror commented 2026-04-12 14:03:34 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jul 24, 2024):

We're constantly adding new model architectures - does this still fail on the latest release?

<!-- gh-comment-id:2246618547 --> @dhiltgen commented on GitHub (Jul 24, 2024): We're constantly adding new model architectures - does this still fail on the latest release?
GiteaMirror commented 2026-04-12 14:03:35 -05:00
Author
Owner
Copy Link

@finnbusse commented on GitHub (Jul 24, 2024):

@dhiltgen Now its working!

<!-- gh-comment-id:2247183782 --> @finnbusse commented on GitHub (Jul 24, 2024): @dhiltgen Now its working!
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#3416
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?