github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1274] "no such file or directory" when creating model during the "creating adapter layer" step #47165

New Issue
Closed
opened 2026-04-28 03:24:00 -05:00 by GiteaMirror · 9 comments
GiteaMirror commented 2026-04-28 03:24:00 -05:00
Owner
Copy Link

Originally created by @meow-d on GitHub (Nov 25, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1274

when i run ollama create storywriter, i get:

transferring model data
reading model metadata
creating template layer
creating system layer
creating adapter layer
Error: open /@sha256:439bdfbd08b0143c5f5f97154d76676a5348a5a00a2fac38fdc8d1c4498d67d3: no such file or directory

btw i'm running on Fedora 39

my Modelfile, just in case:

FROM llama2-uncensored:latest

TEMPLATE """{{ .System }}

### HUMAN:
{{ .Prompt }}

### RESPONSE:
"""

PARAMETER stop "### HUMAN:"
PARAMETER stop "### RESPONSE:"

SYSTEM """
"""

ADAPTER ./adapter_model.bin
Originally created by @meow-d on GitHub (Nov 25, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1274 when i run `ollama create storywriter`, i get: ``` transferring model data reading model metadata creating template layer creating system layer creating adapter layer Error: open /@sha256:439bdfbd08b0143c5f5f97154d76676a5348a5a00a2fac38fdc8d1c4498d67d3: no such file or directory ``` btw i'm running on Fedora 39 my Modelfile, just in case: ``` FROM llama2-uncensored:latest TEMPLATE """{{ .System }} ### HUMAN: {{ .Prompt }} ### RESPONSE: """ PARAMETER stop "### HUMAN:" PARAMETER stop "### RESPONSE:" SYSTEM """ """ ADAPTER ./adapter_model.bin ```
GiteaMirror commented 2026-04-28 03:24:00 -05:00
Author
Owner
Copy Link

@technovangelist commented on GitHub (Nov 26, 2023):

And llama2-uncensored:latest is on your machine and the adapter file is in the same place where you are running that command from?

<!-- gh-comment-id:1826449898 --> @technovangelist commented on GitHub (Nov 26, 2023): And llama2-uncensored:latest is on your machine and the adapter file is in the same place where you are running that command from?
GiteaMirror commented 2026-04-28 03:24:01 -05:00
Author
Owner
Copy Link

@meow-d commented on GitHub (Nov 26, 2023):

no, llama2-uncensored:latest is downloaded using ollama pull. but the adapter file is at the same place. i've tried using absolute paths too, with the same result.

<!-- gh-comment-id:1826473888 --> @meow-d commented on GitHub (Nov 26, 2023): no, llama2-uncensored:latest is downloaded using `ollama pull`. but the adapter file is at the same place. i've tried using absolute paths too, with the same result.
GiteaMirror commented 2026-04-28 03:24:01 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Nov 27, 2023):

Hi @meow-d, this looks like #892 which was fixed in one of the recent releases. I'd suggest updating Ollama and trying again. You can do that by just running the install script again: curl https://ollama.ai/install.sh | sh

<!-- gh-comment-id:1828117194 --> @BruceMacD commented on GitHub (Nov 27, 2023): Hi @meow-d, this looks like #892 which was fixed in one of the recent releases. I'd suggest updating Ollama and trying again. You can do that by just running the install script again: `curl https://ollama.ai/install.sh | sh`
GiteaMirror commented 2026-04-28 03:24:01 -05:00
Author
Owner
Copy Link

@meow-d commented on GitHub (Nov 29, 2023):

thank you. but the problem is still there after i updated.

<!-- gh-comment-id:1831430569 --> @meow-d commented on GitHub (Nov 29, 2023): thank you. but the problem is still there after i updated.
GiteaMirror commented 2026-04-28 03:24:02 -05:00
Author
Owner
Copy Link

@mhunjaai commented on GitHub (Nov 30, 2023):

I got the same problem @BruceMacD on both linux + mac.
In v0.1.9 the problem does not occur on creating the model based on the Modelfile with local adapter path.
However in v0.1.10 till latest it also fails with the error code from above. Maybe this helps.

<!-- gh-comment-id:1833286970 --> @mhunjaai commented on GitHub (Nov 30, 2023): I got the same problem @BruceMacD on both linux + mac. In v0.1.9 the problem does not occur on creating the model based on the Modelfile with local adapter path. However in v0.1.10 till latest it also fails with the error code from above. Maybe this helps.
GiteaMirror commented 2026-04-28 03:24:02 -05:00
Author
Owner
Copy Link

@solablue commented on GitHub (Dec 3, 2023):

@BruceMacD

I am facing the same issue.

transferring context    
reading model metadata    
⠋ creating adapter layer  Error: open /@sha256:ff1527d49453147c6bd4a89ac61c8cb3948aea7d1787b2540330b5df7335e0ba: no such file or directory
<!-- gh-comment-id:1837490380 --> @solablue commented on GitHub (Dec 3, 2023): @BruceMacD I am facing the same issue. ``` transferring context reading model metadata ⠋ creating adapter layer Error: open /@sha256:ff1527d49453147c6bd4a89ac61c8cb3948aea7d1787b2540330b5df7335e0ba: no such file or directory ```
GiteaMirror commented 2026-04-28 03:24:02 -05:00
Author
Owner
Copy Link

@technovangelist commented on GitHub (Jan 3, 2024):

Are folks still experiencing this issue? We are now on 0.1.17 so wondering if it has been solved. If not, perhaps we can get a copy of an adapter that is causing problems, and we can try to recreate the issue. I'm not sure what the right way to send that file over is, so ping here and we can coordinate. Thanks @solablue @meow-d @mhunjaai for being a great part of this remarkable community.

<!-- gh-comment-id:1875742151 --> @technovangelist commented on GitHub (Jan 3, 2024): Are folks still experiencing this issue? We are now on 0.1.17 so wondering if it has been solved. If not, perhaps we can get a copy of an adapter that is causing problems, and we can try to recreate the issue. I'm not sure what the right way to send that file over is, so ping here and we can coordinate. Thanks @solablue @meow-d @mhunjaai for being a great part of this remarkable community.
GiteaMirror commented 2026-04-28 03:24:03 -05:00
Author
Owner
Copy Link

@PhilipAmadasun commented on GitHub (Jan 6, 2024):

@technovangelist I'm having the same "no such file or directory" problems, even after updating my ollama to 0.1.18. Here is a link to my adapter_model.bin here. Oh I realize what's happening. I'm using a server and not my local machine for creation so it's searching for the .bin file on the server machine.

<!-- gh-comment-id:1879512925 --> @PhilipAmadasun commented on GitHub (Jan 6, 2024): @technovangelist I'm having the same "no such file or directory" problems, even after updating my ollama to 0.1.18. Here is a link to my `adapter_model.bin` [here](https://huggingface.co/uyiosa/test_falcon_7b_model/tree/main). Oh I realize what's happening. I'm using a server and not my local machine for creation so it's searching for the `.bin` file on the server machine.
GiteaMirror commented 2026-04-28 03:24:03 -05:00
Author
Owner
Copy Link

@mxyng commented on GitHub (Jan 18, 2024):

This should be fixed now (at least >=0.1.20 but maybe slightly older) where creating a model (including adapters!) should work with remote servers using local files. Please reopen the issue if that's not the case

<!-- gh-comment-id:1899399154 --> @mxyng commented on GitHub (Jan 18, 2024): This should be fixed now (at least >=0.1.20 but maybe slightly older) where creating a model (including adapters!) should work with remote servers using local files. Please reopen the issue if that's not the case
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#47165
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?