github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10000] How do I make a model simply complete my text? #6555

New Issue
Closed
opened 2026-04-12 18:10:51 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-12 18:10:51 -05:00
Owner
Copy Link

Originally created by @Explosion-Scratch on GitHub (Mar 26, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10000

I've been playing around with modelfiles for a while and I can't get the model to simply complete my input, how can I do this?

Originally created by @Explosion-Scratch on GitHub (Mar 26, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10000 I've been playing around with modelfiles for a while and I can't get the model to simply complete my input, how can I do this?
GiteaMirror added the question label 2026-04-12 18:10:51 -05:00
GiteaMirror commented 2026-04-12 18:10:54 -05:00
Author
Owner
Copy Link

@Explosion-Scratch commented on GitHub (Mar 26, 2025):

WHOOA

<!-- gh-comment-id:2754802177 --> @Explosion-Scratch commented on GitHub (Mar 26, 2025): WHOOA
GiteaMirror commented 2026-04-12 18:10:55 -05:00
Author
Owner
Copy Link

@Explosion-Scratch commented on GitHub (Mar 26, 2025):

Issue 10000

<!-- gh-comment-id:2754802446 --> @Explosion-Scratch commented on GitHub (Mar 26, 2025): Issue 10000
GiteaMirror commented 2026-04-12 18:10:56 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 26, 2025):

Don't use a finetuned model, use a base or text model. For example, llama3.2:3b-text-q4_K_M instead of llama3.2:3b-instruct-q4_K_M. Note that most models in the ollama library are finetuned or instruct models, you might need to go to HF to get the base model.

<!-- gh-comment-id:2754827204 --> @rick-github commented on GitHub (Mar 26, 2025): Don't use a finetuned model, use a base or text model. For example, [llama3.2:3b-text-q4_K_M](https://ollama.com/library/llama3.2:3b-text-q4_K_M) instead of [llama3.2:3b-instruct-q4_K_M](https://ollama.com/library/llama3.2:3b-instruct-q4_K_M). Note that most models in the ollama library are finetuned or instruct models, you might need to go to HF to get the base model.
GiteaMirror commented 2026-04-12 18:10:57 -05:00
Author
Owner
Copy Link

@Explosion-Scratch commented on GitHub (Mar 26, 2025):

Don't use a finetuned model, use a base or text model. For example, llama3.2:3b-text-q4_K_M instead of llama3.2:3b-instruct-q4_K_M. Note that most models in the ollama library are finetuned or instruct models, you might need to go to HF to get the base model.

Thanks. Then what should my modelfile look like?

<!-- gh-comment-id:2755588725 --> @Explosion-Scratch commented on GitHub (Mar 26, 2025): > Don't use a finetuned model, use a base or text model. For example, [llama3.2:3b-text-q4_K_M](https://ollama.com/library/llama3.2:3b-text-q4_K_M) instead of [llama3.2:3b-instruct-q4_K_M](https://ollama.com/library/llama3.2:3b-instruct-q4_K_M). Note that most models in the ollama library are finetuned or instruct models, you might need to go to HF to get the base model. Thanks. Then what should my modelfile look like?
GiteaMirror commented 2026-04-12 18:10:58 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 26, 2025):

ollama models come with a Modelfile, so there's no need to create a new one unless you want to tweak parameters like temperature, etc. If that's the case, check the doc.

$ ollama show --modelfile llama3.2:3b-text-q4_K_M
# Modelfile generated by "ollama show"
# To build a new Modelfile based on this, replace FROM with:
# FROM llama3.2:3b-text-q4_K_M

FROM /root/.ollama/models/blobs/sha256-e794be6824b360baedfb10c2f0f277f3ae0c3739539f3e37b0e3836688ec1831
TEMPLATE {{ .Prompt }}
LICENSE "LLAMA 3.2 COMMUNITY LICENSE AGREEMENT
Llama 3.2 Version Release Date: September 25, 2024
...

But you can also set parameters in the API call.

$ curl -s localhost:11434/api/generate -d '{
  "model":"llama3.2:3b-text-q4_K_M",
  "prompt":"The sky appears blue because of a phenomenon called Rayleigh ",
  "options":{"temperature":0,"stop":["\n"]},"stream":false}' | jq .response
" scattering. This is the scattering of light by particles in the atmosphere that are smaller than the wavelength of visible light."
<!-- gh-comment-id:2755652626 --> @rick-github commented on GitHub (Mar 26, 2025): ollama models come with a Modelfile, so there's no need to create a new one unless you want to tweak parameters like `temperature`, etc. If that's the case, check the [doc](https://github.com/ollama/ollama/blob/main/docs/modelfile.md). ```console $ ollama show --modelfile llama3.2:3b-text-q4_K_M # Modelfile generated by "ollama show" # To build a new Modelfile based on this, replace FROM with: # FROM llama3.2:3b-text-q4_K_M FROM /root/.ollama/models/blobs/sha256-e794be6824b360baedfb10c2f0f277f3ae0c3739539f3e37b0e3836688ec1831 TEMPLATE {{ .Prompt }} LICENSE "LLAMA 3.2 COMMUNITY LICENSE AGREEMENT Llama 3.2 Version Release Date: September 25, 2024 ... ``` But you can also set parameters in the API call. ```console $ curl -s localhost:11434/api/generate -d '{ "model":"llama3.2:3b-text-q4_K_M", "prompt":"The sky appears blue because of a phenomenon called Rayleigh ", "options":{"temperature":0,"stop":["\n"]},"stream":false}' | jq .response " scattering. This is the scattering of light by particles in the atmosphere that are smaller than the wavelength of visible light." ```
GiteaMirror commented 2026-04-12 18:10:58 -05:00
Author
Owner
Copy Link

@Explosion-Scratch commented on GitHub (Mar 27, 2025):

Ok! Thanks so much!

<!-- gh-comment-id:2758593960 --> @Explosion-Scratch commented on GitHub (Mar 27, 2025): Ok! Thanks so much!
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 question
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#6555
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?