github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #5869] Error: file does not exist but it exists #65697

New Issue
Open
opened 2026-05-03 22:16:43 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-05-03 22:16:43 -05:00
Owner
Copy Link

Originally created by @DevLLM on GitHub (Jul 23, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5869

Originally assigned to: @BruceMacD on GitHub.

What is the issue?

Hello, I want to push my model to ollama but I got the error

retrieving manifest
Error: file does not exist

but the problem is that I have the file, specifically "C:\Users\User.ollama\models\manifests\registry.ollama.ai_\mymodel\latest"

and my username is _ (link: https://ollama.com/_ ), so and I can't change my username

"""
D:\ollama> ollama create _/mymodel:latest -f Modelfile
transferring model data
using existing layer sha256:617ba424eabae67d228cf4598d2b18d9656b73c1f8f5bfa974ead81485dad2a5
using existing layer sha256:f5dc666b38fce911ccd916bcb13ea78a8002803fd11d5bb6486c4dd76ab8223f
using existing layer sha256:3dddcbf82aec37d515d388e1141900e1530f74f20c5091f64567609a56fe8f43
using existing layer sha256:023c31c9015bbf14d78183c19eec819c3142e791c857bbc3989e53250f00561d
using existing layer sha256:c50ad1ef7469cb081d31e4c321e73562e1e657e890a325b4d7214f8988fd1678
using existing layer sha256:6a6636a5d2ef8c1f29444967fb0f17930369d2c53117d39bd3926760d1062230
writing manifest
success

D:\ollama> ollama list
NAME ID SIZE MODIFIED
_/mymodel:latest 37dad3f2b9d3 13 GB 18 seconds ago
mymodel:latest 37dad3f2b9d3 13 GB 23 minutes ago

D:\ollama> ollama push _/mymodel:latest
retrieving manifest
Error: file does not exist
"""

OS

Windows, WSL2

GPU

Nvidia, Intel

CPU

Intel

Ollama version

0.2.7

Originally created by @DevLLM on GitHub (Jul 23, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5869 Originally assigned to: @BruceMacD on GitHub. ### What is the issue? Hello, I want to push my model to ollama but I got the error `retrieving manifest` `Error: file does not exist ` but the problem is that I have the file, specifically "C:\Users\User\.ollama\models\manifests\registry.ollama.ai\_\mymodel\latest" and my username is _ (link: [https://ollama.com/_](https://ollama.com/_ ) ), so and I can't change my username """ D:\ollama> ollama create _/mymodel:latest -f Modelfile transferring model data using existing layer sha256:617ba424eabae67d228cf4598d2b18d9656b73c1f8f5bfa974ead81485dad2a5 using existing layer sha256:f5dc666b38fce911ccd916bcb13ea78a8002803fd11d5bb6486c4dd76ab8223f using existing layer sha256:3dddcbf82aec37d515d388e1141900e1530f74f20c5091f64567609a56fe8f43 using existing layer sha256:023c31c9015bbf14d78183c19eec819c3142e791c857bbc3989e53250f00561d using existing layer sha256:c50ad1ef7469cb081d31e4c321e73562e1e657e890a325b4d7214f8988fd1678 using existing layer sha256:6a6636a5d2ef8c1f29444967fb0f17930369d2c53117d39bd3926760d1062230 writing manifest success D:\ollama> ollama list NAME ID SIZE MODIFIED _/mymodel:latest 37dad3f2b9d3 13 GB 18 seconds ago mymodel:latest 37dad3f2b9d3 13 GB 23 minutes ago D:\ollama> ollama push _/mymodel:latest retrieving manifest Error: file does not exist """ ### OS Windows, WSL2 ### GPU Nvidia, Intel ### CPU Intel ### Ollama version 0.2.7
GiteaMirror added the bug label 2026-05-03 22:16:43 -05:00
GiteaMirror commented 2026-05-03 22:16:50 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Jul 25, 2024):

Hi @DevLLM, this one slipped past our validation. Send me an email at bruce.macdonald-at-ollama.com and I'll get you switched over to whatever valid namespace you'd like.

<!-- gh-comment-id:2249095169 --> @BruceMacD commented on GitHub (Jul 25, 2024): Hi @DevLLM, this one slipped past our validation. Send me an email at `bruce.macdonald-at-ollama.com` and I'll get you switched over to whatever valid namespace you'd like.
GiteaMirror commented 2026-05-03 22:16:51 -05:00
Author
Owner
Copy Link

@bmizerany commented on GitHub (Jul 25, 2024):

@DevLLM Will you please confirm the path you pasted (C:Users\User.ollama\models\manifests\registry.ollama.ai_\mymodel\latest) is correct? If so, it's also a bug that there is no \ after .ai and before _.

<!-- gh-comment-id:2249148114 --> @bmizerany commented on GitHub (Jul 25, 2024): @DevLLM Will you please confirm the path you pasted (`C:Users\User.ollama\models\manifests\registry.ollama.ai_\mymodel\latest`) is correct? If so, it's also a bug that there is no `\` after `.ai` and before `_`.
GiteaMirror commented 2026-05-03 22:16:52 -05:00
Author
Owner
Copy Link

@Minxiangliu commented on GitHub (Nov 15, 2024):

Hi @BruceMacD , @bmizerany
I tried creating a model and followed this example to execute the ollama commands. Everything went smoothly during the creation process, but when I tried to run the model, it said it couldn't be found. Did I make a mistake somewhere? Could you please help me?
Thank you in advance.

OS

Docker ubuntu22.04 in Windows WSL2

GPU

Nvidia, Intel

CPU

Intel

Ollama version

0.4.1

Modelfile:

# Modelfile
FROM "/build_docker/Llama-3.2/Llama-3.2-11B-Vision-Instruct-mmproj.f16.gguf"

PARAMETER stop "<|im_start|>"
PARAMETER stop "<|im_end|>"

TEMPLATE """
<|im_start|>system
{{ .System }}<|im_end|>
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""

Log:

(py310) root@019a5ec06402:~# ollama create my-own-model -f Modelfile
transferring model data 100%
using existing layer sha256:622429e8d31810962dd984bc98559e706db2fb1d40e99cb073beb7148d909d73
creating new layer sha256:8971eb8e89ce161a65232db6db5019953dbc313fc296d9e6e9d7823e395673b9
creating new layer sha256:f02dd72bb2423204352eabc5637b44d79d17f109fdb510a7c51455892aa2d216
creating new layer sha256:896227e1de4d5b48a7fbf9eec7a095ab38351f5c3efb11cf81f616cb9208570e
writing manifest
success
(py310) root@019a5ec06402:~# ollama list
NAME                   ID              SIZE      MODIFIED
my-own-model:latest    c4901261a022    1.9 GB    About a minute ago
llama3.2:1b            baf6a787fdff    1.3 GB    2 hours ago
(py310) root@019a5ec06402:~# ollama run my-own-model:latest
pulling manifest
Error: pull model manifest: file does not exist
(py310) root@019a5ec06402:~#

ollama serve:

[GIN] 2024/11/15 - 16:38:06 | 200 |      2.5631ms |       127.0.0.1 | POST     "/api/create"
[GIN] 2024/11/15 - 16:38:34 | 200 |        91.4µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/11/15 - 16:38:34 | 200 |       322.4µs |       127.0.0.1 | GET      "/api/tags"
[GIN] 2024/11/15 - 16:38:41 | 200 |        18.3µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/11/15 - 16:38:41 | 200 |       357.1µs |       127.0.0.1 | POST     "/api/generate"
[GIN] 2024/11/15 - 16:38:41 | 200 |    133.8325ms |       127.0.0.1 | DELETE   "/api/delete"
[GIN] 2024/11/15 - 16:38:43 | 200 |          18µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/11/15 - 16:38:43 | 200 |       235.5µs |       127.0.0.1 | GET      "/api/tags"
[GIN] 2024/11/15 - 16:41:16 | 200 |        39.3µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/11/15 - 16:41:29 | 201 |    5.5687215s |       127.0.0.1 | POST     "/api/blobs/sha256:622429e8d31810962dd984bc98559e706db2fb1d40e99cb073beb7148d909d73"
[GIN] 2024/11/15 - 16:41:29 | 200 |      3.1334ms |       127.0.0.1 | POST     "/api/create"
[GIN] 2024/11/15 - 16:42:48 | 200 |        77.5µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/11/15 - 16:42:48 | 200 |       784.1µs |       127.0.0.1 | GET      "/api/tags"
[GIN] 2024/11/15 - 16:43:01 | 200 |        18.4µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/11/15 - 16:43:01 | 404 |       422.2µs |       127.0.0.1 | POST     "/api/show"
[GIN] 2024/11/15 - 16:43:02 | 200 |    1.2704652s |       127.0.0.1 | POST     "/api/pull"
<!-- gh-comment-id:2478249376 --> @Minxiangliu commented on GitHub (Nov 15, 2024): Hi @BruceMacD , @bmizerany I tried creating a [model](https://huggingface.co/leafspark/Llama-3.2-11B-Vision-Instruct-GGUF/tree/main) and followed this [example](https://medium.com/@sudarshan-koirala/ollama-huggingface-8e8bc55ce572) to execute the ollama commands. Everything went smoothly during the creation process, but when I tried to run the model, it said it couldn't be found. Did I make a mistake somewhere? Could you please help me? Thank you in advance. ## OS Docker ubuntu22.04 in Windows WSL2 ## GPU Nvidia, Intel ## CPU Intel ## Ollama version 0.4.1 Modelfile: ``` # Modelfile FROM "/build_docker/Llama-3.2/Llama-3.2-11B-Vision-Instruct-mmproj.f16.gguf" PARAMETER stop "<|im_start|>" PARAMETER stop "<|im_end|>" TEMPLATE """ <|im_start|>system {{ .System }}<|im_end|> <|im_start|>user {{ .Prompt }}<|im_end|> <|im_start|>assistant """ ``` Log: ```log (py310) root@019a5ec06402:~# ollama create my-own-model -f Modelfile transferring model data 100% using existing layer sha256:622429e8d31810962dd984bc98559e706db2fb1d40e99cb073beb7148d909d73 creating new layer sha256:8971eb8e89ce161a65232db6db5019953dbc313fc296d9e6e9d7823e395673b9 creating new layer sha256:f02dd72bb2423204352eabc5637b44d79d17f109fdb510a7c51455892aa2d216 creating new layer sha256:896227e1de4d5b48a7fbf9eec7a095ab38351f5c3efb11cf81f616cb9208570e writing manifest success (py310) root@019a5ec06402:~# ollama list NAME ID SIZE MODIFIED my-own-model:latest c4901261a022 1.9 GB About a minute ago llama3.2:1b baf6a787fdff 1.3 GB 2 hours ago (py310) root@019a5ec06402:~# ollama run my-own-model:latest pulling manifest Error: pull model manifest: file does not exist (py310) root@019a5ec06402:~# ``` ollama serve: ```log [GIN] 2024/11/15 - 16:38:06 | 200 | 2.5631ms | 127.0.0.1 | POST "/api/create" [GIN] 2024/11/15 - 16:38:34 | 200 | 91.4µs | 127.0.0.1 | HEAD "/" [GIN] 2024/11/15 - 16:38:34 | 200 | 322.4µs | 127.0.0.1 | GET "/api/tags" [GIN] 2024/11/15 - 16:38:41 | 200 | 18.3µs | 127.0.0.1 | HEAD "/" [GIN] 2024/11/15 - 16:38:41 | 200 | 357.1µs | 127.0.0.1 | POST "/api/generate" [GIN] 2024/11/15 - 16:38:41 | 200 | 133.8325ms | 127.0.0.1 | DELETE "/api/delete" [GIN] 2024/11/15 - 16:38:43 | 200 | 18µs | 127.0.0.1 | HEAD "/" [GIN] 2024/11/15 - 16:38:43 | 200 | 235.5µs | 127.0.0.1 | GET "/api/tags" [GIN] 2024/11/15 - 16:41:16 | 200 | 39.3µs | 127.0.0.1 | HEAD "/" [GIN] 2024/11/15 - 16:41:29 | 201 | 5.5687215s | 127.0.0.1 | POST "/api/blobs/sha256:622429e8d31810962dd984bc98559e706db2fb1d40e99cb073beb7148d909d73" [GIN] 2024/11/15 - 16:41:29 | 200 | 3.1334ms | 127.0.0.1 | POST "/api/create" [GIN] 2024/11/15 - 16:42:48 | 200 | 77.5µs | 127.0.0.1 | HEAD "/" [GIN] 2024/11/15 - 16:42:48 | 200 | 784.1µs | 127.0.0.1 | GET "/api/tags" [GIN] 2024/11/15 - 16:43:01 | 200 | 18.4µs | 127.0.0.1 | HEAD "/" [GIN] 2024/11/15 - 16:43:01 | 404 | 422.2µs | 127.0.0.1 | POST "/api/show" [GIN] 2024/11/15 - 16:43:02 | 200 | 1.2704652s | 127.0.0.1 | POST "/api/pull" ```
GiteaMirror commented 2026-05-03 22:16:54 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Nov 15, 2024):

Hi @Minxiangliu it looks like your referencing a file that exists in a docker container: FROM "/build_docker/Llama-3.2/Llama-3.2-11B-Vision-Instruct-mmproj.f16.gguf". Is this file accessible from where the ollama server is running?

<!-- gh-comment-id:2479811529 --> @BruceMacD commented on GitHub (Nov 15, 2024): Hi @Minxiangliu it looks like your referencing a file that exists in a docker container: `FROM "/build_docker/Llama-3.2/Llama-3.2-11B-Vision-Instruct-mmproj.f16.gguf"`. Is this file accessible from where the ollama server is running?
GiteaMirror commented 2026-05-03 22:16:55 -05:00
Author
Owner
Copy Link

@Minxiangliu commented on GitHub (Nov 18, 2024):

Hi @BruceMacD ,
Thank you for your reply, and apologies for my late response. After some testing, I was able to use the ollama3.2-vision model on the ollama server. Among these GGUF models, all of them work except for mmproj.f16 model. Thank you! I'll continue testing with the models on the ollama server.

<!-- gh-comment-id:2481739136 --> @Minxiangliu commented on GitHub (Nov 18, 2024): Hi @BruceMacD , Thank you for your reply, and apologies for my late response. After some testing, I was able to use the `ollama3.2-vision` model on the `ollama server`. Among these [GGUF models](https://huggingface.co/leafspark/Llama-3.2-11B-Vision-Instruct-GGUF/tree/main), all of them work except for `mmproj.f16` model. Thank you! I'll continue testing with the models on the `ollama server`.
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#65697
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?