github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 05:36:16 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #4220] modify template, system,or params on webpage #49141

New Issue
Open
opened 2026-04-28 10:49:20 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-28 10:49:20 -05:00
Owner
Copy Link

Originally created by @taozhiyuai on GitHub (May 7, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4220

after pushing a model, sometimes I hope to modify template, system,or params on webpage.

Originally created by @taozhiyuai on GitHub (May 7, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4220 after pushing a model, sometimes I hope to modify template, system,or params on webpage.
GiteaMirror added the feature request label 2026-04-28 10:49:20 -05:00
GiteaMirror commented 2026-04-28 10:49:22 -05:00
Author
Owner
Copy Link

@alwqx commented on GitHub (May 7, 2024):

You can change template, system and params in Modelfile, then recreate model and repush model to ollama.

Or use a base model, then create a new model with different template, system and params.

FROM baseModel
PARAMETER temperature 1
# sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
PARAMETER num_ctx 4096

# sets a custom system message to specify the behavior of the chat assistant
SYSTEM You are Mario from super mario bros, acting as an assistant.

and then ollama create newModel -f Modelfile

<!-- gh-comment-id:2098173456 --> @alwqx commented on GitHub (May 7, 2024): You can change template, system and params in Modelfile, then recreate model and repush model to ollama. Or use a base model, then create a new model with different template, system and params. ```dockerfile FROM baseModel PARAMETER temperature 1 # sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token PARAMETER num_ctx 4096 # sets a custom system message to specify the behavior of the chat assistant SYSTEM You are Mario from super mario bros, acting as an assistant. ``` and then `ollama create newModel -f Modelfile`
GiteaMirror commented 2026-04-28 10:49:22 -05:00
Author
Owner
Copy Link

@taozhiyuai commented on GitHub (May 7, 2024):

You can change template, system and params in Modelfile, then recreate model and repush model to ollama.

Or use a base model, then create a new model with different template, system and params.

FROM baseModel
PARAMETER temperature 1
# sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
PARAMETER num_ctx 4096

# sets a custom system message to specify the behavior of the chat assistant
SYSTEM You are Mario from super mario bros, acting as an assistant.

and then ollama create newModel -f Modelfile

so i must re-push all files,especially that big model. what i wish is to just push a file which contain necessary modification only.

<!-- gh-comment-id:2098356555 --> @taozhiyuai commented on GitHub (May 7, 2024): > You can change template, system and params in Modelfile, then recreate model and repush model to ollama. > > Or use a base model, then create a new model with different template, system and params. > ```dockerfile > FROM baseModel > PARAMETER temperature 1 > # sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token > PARAMETER num_ctx 4096 > > # sets a custom system message to specify the behavior of the chat assistant > SYSTEM You are Mario from super mario bros, acting as an assistant. > ``` > and then `ollama create newModel -f Modelfile` so i must re-push all files,especially that big model. what i wish is to just push a file which contain necessary modification only.
GiteaMirror commented 2026-04-28 10:49:23 -05:00
Author
Owner
Copy Link

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

You can change template, system and params in Modelfile, then recreate model and repush model to ollama.

Or use a base model, then create a new model with different template, system and params.

FROM baseModel
PARAMETER temperature 1
# sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
PARAMETER num_ctx 4096

# sets a custom system message to specify the behavior of the chat assistant
SYSTEM You are Mario from super mario bros, acting as an assistant.

and then ollama create newModel -f Modelfile

so i must re-push all files,especially that big model. what i wish is to just push a file which contain necessary modification only.

If you do the FROM baseModel approach it should actually use the same model files on the system in the model cache folder but only override parameters you are manually setting as needed. Should not have an impact on your storage.

<!-- gh-comment-id:2101674510 --> @Skarian commented on GitHub (May 8, 2024): > > You can change template, system and params in Modelfile, then recreate model and repush model to ollama. > > > > Or use a base model, then create a new model with different template, system and params. > > ```dockerfile > > FROM baseModel > > PARAMETER temperature 1 > > # sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token > > PARAMETER num_ctx 4096 > > > > # sets a custom system message to specify the behavior of the chat assistant > > SYSTEM You are Mario from super mario bros, acting as an assistant. > > ``` > > and then `ollama create newModel -f Modelfile` > > so i must re-push all files,especially that big model. what i wish is to just push a file which contain necessary modification only. If you do the FROM baseModel approach it should actually use the same model files on the system in the model cache folder but only override parameters you are manually setting as needed. Should not have an impact on your storage.
GiteaMirror commented 2026-04-28 10:49:23 -05:00
Author
Owner
Copy Link

@taozhiyuai commented on GitHub (May 9, 2024):

You can change template, system and params in Modelfile, then recreate model and repush model to ollama.
Or use a base model, then create a new model with different template, system and params.

FROM baseModel
PARAMETER temperature 1
# sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
PARAMETER num_ctx 4096

# sets a custom system message to specify the behavior of the chat assistant
SYSTEM You are Mario from super mario bros, acting as an assistant.

and then ollama create newModel -f Modelfile

so i must re-push all files,especially that big model. what i wish is to just push a file which contain necessary modification only.

If you do the FROM baseModel approach it should actually use the same model files on the system in the model cache folder but only override parameters you are manually setting as needed. Should not have an impact on your storage.

for example, I push a model A + template A to ollama.com; then I modify template A to B, and create a model A + template B on my laptop, if I want to push new one to ollama.com, I must re-push model A again. it is time consuming. so , I wish I can modify template A which I have uploaded to ollama.com to template B.so I need not to re-push model A.

<!-- gh-comment-id:2101820026 --> @taozhiyuai commented on GitHub (May 9, 2024): > > > You can change template, system and params in Modelfile, then recreate model and repush model to ollama. > > > Or use a base model, then create a new model with different template, system and params. > > > ```dockerfile > > > FROM baseModel > > > PARAMETER temperature 1 > > > # sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token > > > PARAMETER num_ctx 4096 > > > > > > # sets a custom system message to specify the behavior of the chat assistant > > > SYSTEM You are Mario from super mario bros, acting as an assistant. > > > ``` > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > and then `ollama create newModel -f Modelfile` > > > > > > so i must re-push all files,especially that big model. what i wish is to just push a file which contain necessary modification only. > > If you do the FROM baseModel approach it should actually use the same model files on the system in the model cache folder but only override parameters you are manually setting as needed. Should not have an impact on your storage. for example, I push a model A + template A to ollama.com; then I modify template A to B, and create a model A + template B on my laptop, if I want to push new one to ollama.com, I must re-push model A again. it is time consuming. so , I wish I can modify template A which I have uploaded to ollama.com to template B.so I need not to re-push model A.
GiteaMirror commented 2026-04-28 10:49:24 -05:00
Author
Owner
Copy Link

@taozhiyuai commented on GitHub (May 9, 2024):

You can change template, system and params in Modelfile, then recreate model and repush model to ollama.
Or use a base model, then create a new model with different template, system and params.

FROM baseModel
PARAMETER temperature 1
# sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
PARAMETER num_ctx 4096

# sets a custom system message to specify the behavior of the chat assistant
SYSTEM You are Mario from super mario bros, acting as an assistant.

and then ollama create newModel -f Modelfile

so i must re-push all files,especially that big model. what i wish is to just push a file which contain necessary modification only.

If you do the FROM baseModel approach it should actually use the same model files on the system in the model cache folder but only override parameters you are manually setting as needed. Should not have an impact on your storage.

for example, I push a model A + template A to ollama.com; then I modify template A to B, and create a model A + template B on my laptop, if I want to push new one to ollama.com, I must re-push model A again. it is time consuming. so , I wish I can modify template A which I have uploaded to ollama.com to template B.so I need not to re-push model A.

<!-- gh-comment-id:2101820529 --> @taozhiyuai commented on GitHub (May 9, 2024): > > > You can change template, system and params in Modelfile, then recreate model and repush model to ollama. > > > Or use a base model, then create a new model with different template, system and params. > > > ```dockerfile > > > FROM baseModel > > > PARAMETER temperature 1 > > > # sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token > > > PARAMETER num_ctx 4096 > > > > > > # sets a custom system message to specify the behavior of the chat assistant > > > SYSTEM You are Mario from super mario bros, acting as an assistant. > > > ``` > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > and then `ollama create newModel -f Modelfile` > > > > > > so i must re-push all files,especially that big model. what i wish is to just push a file which contain necessary modification only. > > If you do the FROM baseModel approach it should actually use the same model files on the system in the model cache folder but only override parameters you are manually setting as needed. Should not have an impact on your storage. for example, I push a model A + template A to ollama.com; then I modify template A to B, and create a model A + template B on my laptop, if I want to push new one to ollama.com, I must re-push model A again. it is time consuming. so , I wish I can modify template A which I have uploaded to ollama.com to template B.so I need not to re-push model A.
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 feature request
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#49141
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?