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 #4114] ollama create tries to pull model when using quotes in FROM line #2556

New Issue
Closed
opened 2026-04-12 12:52:52 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 12:52:52 -05:00
Owner
Copy Link

Originally created by @savareyhano on GitHub (May 3, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4114

What is the issue?

Steps to reproduce:

  1. Download and install Ollama v0.1.33 from release page
  2. Download any gguf file and make a modelfile for the gguf file (for example, im using hermes 2 pro):
    Modelfile 
    FROM "./Hermes-2-Pro-Mistral-7B.Q8_0.gguf"
TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
"""
PARAMETER stop <|im_start|>
PARAMETER stop <|im_end|>
PARAMETER num_ctx 4096
  3. Create the model from the modelfile 
    ollama create hermes2-pro-mistral:7b-q8_0 -f ./Modelfile
  4. Run ollama list and see if the model is registered from the modelfile (it is not).

Rolled back to Ollama v0.1.32, and it is now working again so i'm pretty sure this is a problem with the version 0.1.33.

OS

Windows

GPU

Nvidia

CPU

AMD

Ollama version

0.1.33

Originally created by @savareyhano on GitHub (May 3, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4114 ### What is the issue? Steps to reproduce: 1. Download and install [Ollama v0.1.33 from release page](https://github.com/ollama/ollama/releases/tag/v0.1.33) 2. Download any gguf file and make a modelfile for the gguf file (for example, im using hermes 2 pro): Modelfile ``` FROM "./Hermes-2-Pro-Mistral-7B.Q8_0.gguf" TEMPLATE """{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user {{ .Prompt }}<|im_end|> {{ end }}<|im_start|>assistant """ PARAMETER stop <|im_start|> PARAMETER stop <|im_end|> PARAMETER num_ctx 4096 ``` 4. Create the model from the modelfile ```bash ollama create hermes2-pro-mistral:7b-q8_0 -f ./Modelfile ``` 5. Run `ollama list` and see if the model is registered from the modelfile (it is not). Rolled back to [Ollama v0.1.32](https://github.com/ollama/ollama/releases/tag/v0.1.32), and it is now working again so i'm pretty sure this is a problem with the version 0.1.33. ### OS Windows ### GPU Nvidia ### CPU AMD ### Ollama version 0.1.33
GiteaMirror added the bug label 2026-04-12 12:52:52 -05:00
GiteaMirror commented 2026-04-12 12:52:54 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 3, 2024):

Hi @savareyhano thanks for the issue and sorry this happened. It seems removing the quotes around FROM should fix this, but we'll take a look and make sure quotes work on every command

<!-- gh-comment-id:2092006861 --> @jmorganca commented on GitHub (May 3, 2024): Hi @savareyhano thanks for the issue and sorry this happened. It seems removing the quotes around `FROM` should fix this, but we'll take a look and make sure quotes work on every command
GiteaMirror commented 2026-04-12 12:52:55 -05:00
Author
Owner
Copy Link

@github-office commented on GitHub (May 5, 2024):

If you're using windwos, in the Modelfile file, change the file path to C:\Users\ABC\Downloads\ollama\qwen1_5-0_5b-chat-q8_0.gguf to try

<!-- gh-comment-id:2094546677 --> @github-office commented on GitHub (May 5, 2024): If you're using windwos, in the Modelfile file, change the file path to C:\\Users\\ABC\\Downloads\\ollama\\qwen1_5-0_5b-chat-q8_0.gguf to try
GiteaMirror commented 2026-04-12 12:52:55 -05:00
Author
Owner
Copy Link

@savareyhano commented on GitHub (May 8, 2024):

all good now, this is fixed with the version v0.1.34 now it is correctly reading FROM using quotes, thanks @jmorganca

<!-- gh-comment-id:2099791356 --> @savareyhano commented on GitHub (May 8, 2024): all good now, this is fixed with the version [v0.1.34](https://github.com/ollama/ollama/releases/tag/v0.1.34) now it is correctly reading `FROM` using quotes, thanks @jmorganca
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#2556
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?