github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 13:19:40 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #1667] Fails to load larger models, weight not found #47449

New Issue
Closed
opened 2026-04-28 03:49:30 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 03:49:30 -05:00
Owner
Copy Link

Originally created by @spikespaz on GitHub (Dec 22, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1667

Linux odyssey 6.6.6 #1-NixOS SMP PREEMPT_DYNAMIC Mon Dec 11 09:40:17 UTC 2023 x86_64 GNU/Linux

I have attempted to run: dolphin-mixtral, mixtral:8x7b, jmorgan/mixtral, mistral, llama2.

mistral and llama2 work fine, but the others all fail with the same error message:

error loading model: create_tensor: tensor 'blk.0.ffn_gate.weight' not found llama_load_model_from_file: failed to load model

The full output is included as a file.

ollama-log.txt

Originally created by @spikespaz on GitHub (Dec 22, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1667 ``` Linux odyssey 6.6.6 #1-NixOS SMP PREEMPT_DYNAMIC Mon Dec 11 09:40:17 UTC 2023 x86_64 GNU/Linux ``` I have attempted to run: `dolphin-mixtral`, `mixtral:8x7b`, `jmorgan/mixtral`, `mistral`, `llama2`. `mistral` and `llama2` work fine, but the others all fail with the same error message: ``` error loading model: create_tensor: tensor 'blk.0.ffn_gate.weight' not found llama_load_model_from_file: failed to load model ``` The full output is included as a file. [ollama-log.txt](https://github.com/jmorganca/ollama/files/13748283/ollama-log.txt)
GiteaMirror commented 2026-04-28 03:49:31 -05:00
Author
Owner
Copy Link

@easp commented on GitHub (Dec 22, 2023):

The nix package doesn't automatically require the right version of the llama.cpp package. Make sure that's at the right commit.

<!-- gh-comment-id:1867248577 --> @easp commented on GitHub (Dec 22, 2023): The nix package doesn't automatically require the right version of the llama.cpp package. Make sure that's at the right commit.
GiteaMirror commented 2026-04-28 03:49:33 -05:00
Author
Owner
Copy Link

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

I think you were just running out of memory when you were trying to run the model. We've made several changes around how we handle memory since you filed this, so if you update to 0.1.28 and try again (depending on how much system memory you have, of course) it will probably work.

I'm going to go ahead and close out the issue, but feel free to keep commenting or reopen it if you have any questions.

<!-- gh-comment-id:1989565079 --> @pdevine commented on GitHub (Mar 11, 2024): I think you were just running out of memory when you were trying to run the model. We've made several changes around how we handle memory since you filed this, so if you update to 0.1.28 and try again (depending on how much system memory you have, of course) it will probably work. I'm going to go ahead and close out the issue, but feel free to keep commenting or reopen it if you have any questions.
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
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#47449
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?