github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-23 06:01:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #8468] .create() giving out ResponseError #67505

New Issue
Closed
opened 2026-05-04 10:35:13 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-05-04 10:35:13 -05:00
Owner
Copy Link

Originally created by @ShivamSrng on GitHub (Jan 17, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8468

What is the issue?

OS
Windows

GPU
Nvidia 3070Ti
NVIDIA-SMI 566.36
Driver Version: 566.36
CUDA Version: 12.7

CPU
Intel

Ollama version
0.5.7

Model
llama3.1:8b

The model file I am writing is:

modelfile = """
FROM llama3.1

PARAMETER seed 42
PARAMETER temperature 0

SYSTEM ....the prompt .....
"""

ollama.create(
  model="a_generic_model_name",
  modelfile=modelfile
)

I am using Ollama via Python using the library mentioned in the documentation. While passing the prompt, I continuously face this issue: ResponseError: neither 'from' nor 'files' was specified. Can I get some suggestions on how to overcome this issue?

Thanks

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.5.7

Originally created by @ShivamSrng on GitHub (Jan 17, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8468 ### What is the issue? **OS** Windows **GPU** Nvidia 3070Ti NVIDIA-SMI 566.36 Driver Version: 566.36 CUDA Version: 12.7 **CPU** Intel **Ollama version** 0.5.7 **Model** llama3.1:8b The model file I am writing is: ``` modelfile = """ FROM llama3.1 PARAMETER seed 42 PARAMETER temperature 0 SYSTEM ....the prompt ..... """ ollama.create( model="a_generic_model_name", modelfile=modelfile ) ``` I am using Ollama via Python using the library mentioned in the documentation. While passing the prompt, I continuously face this issue: **ResponseError: neither 'from' nor 'files' was specified**. Can I get some suggestions on how to overcome this issue? Thanks ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.5.7
GiteaMirror added the bug label 2026-05-04 10:35:13 -05:00
GiteaMirror commented 2026-05-04 10:35:15 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jan 17, 2025):

Hi @ShivamSrng , this API just changed to make it more RESTful. You can instead call:

ollama.create(
  model="a_generic_model_name",
  from_="llama3.1",
  parameters={"seed": 42, "temperature": 0},
  system="... the prompt ... "
)
<!-- gh-comment-id:2597545980 --> @pdevine commented on GitHub (Jan 17, 2025): Hi @ShivamSrng , this API just changed to make it more RESTful. You can instead call: ``` ollama.create( model="a_generic_model_name", from_="llama3.1", parameters={"seed": 42, "temperature": 0}, system="... the prompt ... " ) ```
GiteaMirror commented 2026-05-04 10:35:16 -05:00
Author
Owner
Copy Link

@ShivamSrng commented on GitHub (Jan 17, 2025):

Hi @ShivamSrng , this API just changed to make it more RESTful. You can instead call:

ollama.create(
  model="a_generic_model_name",
  from_="llama3.1",
  parameters={"seed": 42, "temperature": 0},
  system="... the prompt ... "
)

Thank you very much, for the fast response. And yes, it is resolved now, I forgot to realize the API got updated recently, and I'll go through the documentation once again for such issues.

<!-- gh-comment-id:2597562557 --> @ShivamSrng commented on GitHub (Jan 17, 2025): > Hi [@ShivamSrng](https://github.com/ShivamSrng) , this API just changed to make it more RESTful. You can instead call: > > ``` > ollama.create( > model="a_generic_model_name", > from_="llama3.1", > parameters={"seed": 42, "temperature": 0}, > system="... the prompt ... " > ) > ``` Thank you very much, for the fast response. And yes, it is resolved now, I forgot to realize the API got updated recently, and I'll go through the documentation once again for such issues.
GiteaMirror commented 2026-05-04 10:35:17 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jan 17, 2025):

Glad you got it working! I'll go ahead and close the issue.

<!-- gh-comment-id:2597597893 --> @pdevine commented on GitHub (Jan 17, 2025): Glad you got it working! I'll go ahead and close the issue.
GiteaMirror commented 2026-05-04 10:35:18 -05:00
Author
Owner
Copy Link

@indigotechtutorials commented on GitHub (Jan 18, 2025):

Hey thank you this syntax worked for me

<!-- gh-comment-id:2599498261 --> @indigotechtutorials commented on GitHub (Jan 18, 2025): Hey thank you this syntax worked for me
GiteaMirror commented 2026-05-04 10:35:19 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jan 18, 2025):

@indigotechtutorials is there a specific doc that you were looking at that we missed?

<!-- gh-comment-id:2599524782 --> @pdevine commented on GitHub (Jan 18, 2025): @indigotechtutorials is there a specific doc that you were looking at that we missed?
GiteaMirror commented 2026-05-04 10:35:20 -05:00
Author
Owner
Copy Link

@indigotechtutorials commented on GitHub (Jan 18, 2025):

@pdevine I was talking about updating the docs for the Ruby gem. I added my own PR there.

<!-- gh-comment-id:2599527724 --> @indigotechtutorials commented on GitHub (Jan 18, 2025): @pdevine I was talking about updating the docs for the Ruby gem. I added my own PR there.
GiteaMirror commented 2026-05-04 10:35:21 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jan 18, 2025):

@indigotechtutorials ah, great. Thank you so much! That project isn't maintained by us.

<!-- gh-comment-id:2599532728 --> @pdevine commented on GitHub (Jan 18, 2025): @indigotechtutorials ah, great. Thank you so much! That project isn't maintained by us.
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#67505
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?