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 #4635] Failure to push llama3 and mistral:0.3 with custom parameters to ollama model registry #28672

New Issue
Closed
opened 2026-04-22 07:09:51 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-22 07:09:51 -05:00
Owner
Copy Link

Originally created by @fabceolin on GitHub (May 25, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4635

Originally assigned to: @bmizerany on GitHub.

What is the issue?

The ollama is failing to push images to ollama model registry for llama3 and mistral v0.3

ollama --version
ollama version is 0.1.38

commands to reproduce

ollama pull llama3:instruct
cat <<EOF >Modelfile
FROM llama3:instruct
# Set parameters
PARAMETER temperature 0.8
PARAMETER stop Result
SYSTEM """"""
EOF
ollama create -f Modelfile fabceolin/llama3
ollama push fabceolin/llama3

local server logs

May 25 11:17:06 dev ollama[11383]: [GIN] 2024/05/25 - 11:17:06 | 200 |      54.814µs |       127.0.0.1 | HEAD     "/"
May 25 11:17:06 dev ollama[11383]: [GIN] 2024/05/25 - 11:17:06 | 200 |    1.419569ms |       127.0.0.1 | GET      "/api/tags"
May 25 11:17:37 dev ollama[11383]: [GIN] 2024/05/25 - 11:17:37 | 200 |      19.142µs |       127.0.0.1 | HEAD     "/"
May 25 11:17:43 dev ollama[11383]: panic: runtime error: index out of range [0] with length 0
May 25 11:17:43 dev ollama[11383]: goroutine 23 [running]:
May 25 11:17:43 dev ollama[11383]: github.com/ollama/ollama/server.(*blobUpload).Prepare(0xc0006000e0, {0x12083a20, 0xc0005b00f0}, 0xc00040e990, 0xc00060e240)
May 25 11:17:43 dev ollama[11383]:         github.com/ollama/ollama/server/upload.go:109 +0x9e5
May 25 11:17:43 dev ollama[11383]: github.com/ollama/ollama/server.uploadBlob({0x12083a20, 0xc0005b00f0}, {{0x1256213, 0x5}, {0x1269913, 0x12}, {0xc0005b6030, 0x9}, {0xc0005b603a, 0x6}, ...}, ...)
May 25 11:17:43 dev ollama[11383]:         github.com/ollama/ollama/server/upload.go:389 +0x6cd
May 25 11:17:43 dev ollama[11383]: github.com/ollama/ollama/server.PushModel({0x12083a20, 0xc0005b00f0}, {0xc0005b6030?, 0x4ca0000045a?}, 0xc00060e240, 0xc000045f88)
May 25 11:17:43 dev ollama[11383]:         github.com/ollama/ollama/server/images.go:799 +0x37c
May 25 11:17:43 dev ollama[11383]: github.com/ollama/ollama/server.(*Server).PushModelHandler.func1()
May 25 11:17:43 dev ollama[11383]:         github.com/ollama/ollama/server/routes.go:496 +0x12b
May 25 11:17:43 dev ollama[11383]: created by github.com/ollama/ollama/server.(*Server).PushModelHandler in goroutine 21
May 25 11:17:43 dev ollama[11383]:         github.com/ollama/ollama/server/routes.go:483 +0x186
May 25 11:17:43 dev systemd[1]: ollama.service: Main process exited, code=exited, status=2/INVALIDARGUMENT
May 25 11:17:43 dev systemd[1]: ollama.service: Failed with result 'exit-code'.
May 25 11:17:43 dev systemd[1]: ollama.service: Consumed 5.298s CPU time.

I had the same issue with mistral version v0.3 instruct.

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.1.38

Originally created by @fabceolin on GitHub (May 25, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4635 Originally assigned to: @bmizerany on GitHub. ### What is the issue? The ollama is failing to push images to ollama model registry for llama3 and mistral v0.3 ``` ollama --version ollama version is 0.1.38 ``` commands to reproduce ``` ollama pull llama3:instruct cat <<EOF >Modelfile FROM llama3:instruct # Set parameters PARAMETER temperature 0.8 PARAMETER stop Result SYSTEM """""" EOF ollama create -f Modelfile fabceolin/llama3 ollama push fabceolin/llama3 ``` local server logs ``` May 25 11:17:06 dev ollama[11383]: [GIN] 2024/05/25 - 11:17:06 | 200 | 54.814µs | 127.0.0.1 | HEAD "/" May 25 11:17:06 dev ollama[11383]: [GIN] 2024/05/25 - 11:17:06 | 200 | 1.419569ms | 127.0.0.1 | GET "/api/tags" May 25 11:17:37 dev ollama[11383]: [GIN] 2024/05/25 - 11:17:37 | 200 | 19.142µs | 127.0.0.1 | HEAD "/" May 25 11:17:43 dev ollama[11383]: panic: runtime error: index out of range [0] with length 0 May 25 11:17:43 dev ollama[11383]: goroutine 23 [running]: May 25 11:17:43 dev ollama[11383]: github.com/ollama/ollama/server.(*blobUpload).Prepare(0xc0006000e0, {0x12083a20, 0xc0005b00f0}, 0xc00040e990, 0xc00060e240) May 25 11:17:43 dev ollama[11383]: github.com/ollama/ollama/server/upload.go:109 +0x9e5 May 25 11:17:43 dev ollama[11383]: github.com/ollama/ollama/server.uploadBlob({0x12083a20, 0xc0005b00f0}, {{0x1256213, 0x5}, {0x1269913, 0x12}, {0xc0005b6030, 0x9}, {0xc0005b603a, 0x6}, ...}, ...) May 25 11:17:43 dev ollama[11383]: github.com/ollama/ollama/server/upload.go:389 +0x6cd May 25 11:17:43 dev ollama[11383]: github.com/ollama/ollama/server.PushModel({0x12083a20, 0xc0005b00f0}, {0xc0005b6030?, 0x4ca0000045a?}, 0xc00060e240, 0xc000045f88) May 25 11:17:43 dev ollama[11383]: github.com/ollama/ollama/server/images.go:799 +0x37c May 25 11:17:43 dev ollama[11383]: github.com/ollama/ollama/server.(*Server).PushModelHandler.func1() May 25 11:17:43 dev ollama[11383]: github.com/ollama/ollama/server/routes.go:496 +0x12b May 25 11:17:43 dev ollama[11383]: created by github.com/ollama/ollama/server.(*Server).PushModelHandler in goroutine 21 May 25 11:17:43 dev ollama[11383]: github.com/ollama/ollama/server/routes.go:483 +0x186 May 25 11:17:43 dev systemd[1]: ollama.service: Main process exited, code=exited, status=2/INVALIDARGUMENT May 25 11:17:43 dev systemd[1]: ollama.service: Failed with result 'exit-code'. May 25 11:17:43 dev systemd[1]: ollama.service: Consumed 5.298s CPU time. ``` I had the same issue with mistral version v0.3 instruct. ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.38
GiteaMirror added the needs more infobug labels 2026-04-22 07:09:51 -05:00
GiteaMirror commented 2026-04-22 07:09:54 -05:00
Author
Owner
Copy Link

@jimscard commented on GitHub (May 26, 2024):

You didn't specify any tags on the CLI. What happens if you do a ollama push fabceolin/llama3:instruct or ollama push fabceolin/llama3:latest ?

<!-- gh-comment-id:2132017856 --> @jimscard commented on GitHub (May 26, 2024): You didn't specify any tags on the CLI. What happens if you do a `ollama push fabceolin/llama3:instruct` or `ollama push fabceolin/llama3:latest` ?
GiteaMirror commented 2026-04-22 07:09:55 -05:00
Author
Owner
Copy Link

@fabceolin commented on GitHub (May 26, 2024):

Same error with

ollama push fabceolin/llama3:instruct

and

ollama push fabceolin/llama3:latest

With llama2, the push is done correctly.

<!-- gh-comment-id:2132190246 --> @fabceolin commented on GitHub (May 26, 2024): Same error with ``` ollama push fabceolin/llama3:instruct ``` and ``` ollama push fabceolin/llama3:latest ``` With llama2, the push is done correctly.
GiteaMirror commented 2026-04-22 07:09:55 -05:00
Author
Owner
Copy Link

@bmizerany commented on GitHub (Sep 14, 2024):

@fabceolin If you upgrade to the latest version (0.3.10 at the time of writing) does the issue persist?

<!-- gh-comment-id:2351226043 --> @bmizerany commented on GitHub (Sep 14, 2024): @fabceolin If you upgrade to the latest version (0.3.10 at the time of writing) does the issue persist?
GiteaMirror commented 2026-04-22 07:09:56 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Sep 15, 2024):

@fabceolin sorry for the slow response. It looks like you were able to create the llama3 model repo on ollama.com, but nothing got pushed to it.

<!-- gh-comment-id:2351632632 --> @pdevine commented on GitHub (Sep 15, 2024): @fabceolin sorry for the slow response. It looks like you were able to create the llama3 model repo on ollama.com, but nothing got pushed to it.
GiteaMirror commented 2026-04-22 07:09:57 -05:00
Author
Owner
Copy Link

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

I'm going to go ahead and close this, but we can reopen it if it's still a problem (and apologies for the slow response!)

<!-- gh-comment-id:2430749064 --> @pdevine commented on GitHub (Oct 23, 2024): I'm going to go ahead and close this, but we can reopen it if it's still a problem (and apologies for the slow response!)
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 needs more info
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#28672
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?