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 #2059] Model info include model type #26952

New Issue
Open
opened 2026-04-22 03:44:56 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 03:44:56 -05:00
Owner
Copy Link

Originally created by @iplayfast on GitHub (Jan 18, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2059

Enhancement request:
I've recently come across an issue where a model was a autocompletion model and not a chat/instruct model. (model is stable-code)
As these models work in very different ways there should be a way to programatically know what type of usage the mode should have.
https://github.com/jmorganca/ollama/issues/2025

I'm not sure of the best solution, but the current state is very confusing since most of the models in ollama are chat/instruct.

Originally created by @iplayfast on GitHub (Jan 18, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2059 Enhancement request: I've recently come across an issue where a model was a autocompletion model and not a chat/instruct model. (model is stable-code) As these models work in very different ways there should be a way to programatically know what type of usage the mode should have. https://github.com/jmorganca/ollama/issues/2025 I'm not sure of the best solution, but the current state is very confusing since most of the models in ollama are chat/instruct.
GiteaMirror added the feature request label 2026-04-22 03:44:56 -05:00
GiteaMirror commented 2026-04-22 03:44:57 -05:00
Author
Owner
Copy Link

@iplayfast commented on GitHub (Jan 30, 2024):

Bit me again.
Code completion models are so different than chat models there should be a way that:

  1. they can be recognised.
  2. a query can have a maximum response time.
  3. a query can have a maximum response length
    For fun try running
ollama run sqlcoder

Try the following querys in order
"Hello"
"what areas of knowledge do you have?"
"can you create code and if so what are your best languages."
"Create a python program to capture a wave file when sound is happening, when done print the name of the wave file"
"what fills you with joy?"

At some point it will just go crazy.

<!-- gh-comment-id:1916160950 --> @iplayfast commented on GitHub (Jan 30, 2024): Bit me again. Code completion models are so different than chat models there should be a way that: 1. they can be recognised. 2. a query can have a maximum response time. 3. a query can have a maximum response length For fun try running ``` ollama run sqlcoder ``` Try the following querys in order "Hello" "what areas of knowledge do you have?" "can you create code and if so what are your best languages." "Create a python program to capture a wave file when sound is happening, when done print the name of the wave file" "what fills you with joy?" At some point it will just go crazy.
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#26952
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?