github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3542] Push of new model #48695

New Issue
Closed
opened 2026-04-28 09:06:25 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 09:06:25 -05:00
Owner
Copy Link

Originally created by @emsi on GitHub (Apr 8, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3542

What is the issue?

When trying to push NEW model I get Error: file does not exist.

I have debugged it under mitm and it seems ollama server tries to HEAD the new, nonexisting, model:

[19:36:39.502][172.17.0.1:52910] server connect registry.ollama.ai:443 (104.21.75.227:443)
172.17.0.1:52910: HEAD https://registry.ollama.ai/v2/emsi/Qra-13b/blobs/sha256:d381585268275794b5c658640369b3c112d982a0fef343da4bf50404bfe9e03f
               << 404 Not Found 0b
172.17.0.1:52910: POST https://registry.ollama.ai/v2/emsi/Qra-13b/blobs/uploads/
               << 404 Not Found 19b

What did you expect to see?

It should upload.

Steps to reproduce

Create a completely new model then:

root@105638d575be:/# ollama -v
ollama version is 0.1.30
root@105638d575be:/# ollama run emsi/Qra-13b
>>> Send a message (/? for help)
root@105638d575be:/# ollama push emsi/Qra-13b
retrieving manifest 
Error: file does not exist

Are there any recent changes that introduced the issue?

No response

OS

Linux

Architecture

No response

Platform

Docker

Ollama version

0.1.30

GPU

Nvidia

GPU info

No response

CPU

No response

Other software

No response

Originally created by @emsi on GitHub (Apr 8, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3542 ### What is the issue? When trying to push NEW model I get `Error: file does not exist`. I have debugged it under mitm and it seems ollama server tries to HEAD the new, nonexisting, model: ``` [19:36:39.502][172.17.0.1:52910] server connect registry.ollama.ai:443 (104.21.75.227:443) 172.17.0.1:52910: HEAD https://registry.ollama.ai/v2/emsi/Qra-13b/blobs/sha256:d381585268275794b5c658640369b3c112d982a0fef343da4bf50404bfe9e03f << 404 Not Found 0b 172.17.0.1:52910: POST https://registry.ollama.ai/v2/emsi/Qra-13b/blobs/uploads/ << 404 Not Found 19b ``` ### What did you expect to see? It should upload. ### Steps to reproduce Create a completely new model then: ``` root@105638d575be:/# ollama -v ollama version is 0.1.30 root@105638d575be:/# ollama run emsi/Qra-13b >>> Send a message (/? for help) root@105638d575be:/# ollama push emsi/Qra-13b retrieving manifest Error: file does not exist ``` ### Are there any recent changes that introduced the issue? _No response_ ### OS Linux ### Architecture _No response_ ### Platform Docker ### Ollama version 0.1.30 ### GPU Nvidia ### GPU info _No response_ ### CPU _No response_ ### Other software _No response_
GiteaMirror added the bug label 2026-04-28 09:06:25 -05:00
GiteaMirror commented 2026-04-28 09:06:27 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Apr 8, 2024):

Hi there, sorry about this. Model names in Ollama can only have lowercase characters. If you rename the model to emsi/qra-13b it should work. emsi/qra:13b is also another name I'd recommend 😊 . Will merge this with https://github.com/ollama/ollama/issues/3297

<!-- gh-comment-id:2043612359 --> @jmorganca commented on GitHub (Apr 8, 2024): Hi there, sorry about this. Model names in Ollama can only have lowercase characters. If you rename the model to `emsi/qra-13b` it should work. `emsi/qra:13b` is also another name I'd recommend 😊 . Will merge this with https://github.com/ollama/ollama/issues/3297
GiteaMirror commented 2026-04-28 09:06:28 -05:00
Author
Owner
Copy Link

@emsi commented on GitHub (Apr 9, 2024):

Hi!

Thanks @jmorganca for the replay. It's a pitty that web UI offers a vaidator while ollama itself just spits out a bogus error message that gives no clue about the cause of the problem.

<!-- gh-comment-id:2045323231 --> @emsi commented on GitHub (Apr 9, 2024): Hi! Thanks @jmorganca for the replay. It's a pitty that web UI offers a vaidator while ollama itself just spits out a bogus error message that gives no clue about the cause of the problem.
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#48695
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?