github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #3644] Is the model's PROMPT maximum number of tokens determined by the inference tool? #2247

New Issue
Closed
opened 2026-04-12 12:31:18 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 12:31:18 -05:00
Owner
Copy Link

Originally created by @17Reset on GitHub (Apr 15, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3644

When I use ollama to reason about my Smuag-72B's model, there is no output when the input prompt has 150tokens, but the output is normal when scaled down to about 100.

Originally created by @17Reset on GitHub (Apr 15, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3644 When I use ollama to reason about my Smuag-72B's model, there is no output when the input prompt has 150tokens, but the output is normal when scaled down to about 100.
GiteaMirror commented 2026-04-12 12:31:19 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Apr 15, 2024):

Hi there, the context window defaults to 2048 and can be overridden with the num_ctx option: https://github.com/ollama/ollama/blob/main/docs/api.md#generate-request-with-options

<!-- gh-comment-id:2057646417 --> @jmorganca commented on GitHub (Apr 15, 2024): Hi there, the context window defaults to 2048 and can be overridden with the `num_ctx` option: https://github.com/ollama/ollama/blob/main/docs/api.md#generate-request-with-options
GiteaMirror commented 2026-04-12 12:31:19 -05:00
Author
Owner
Copy Link

@17Reset commented on GitHub (Apr 16, 2024):

Again it doesn't work, even if I boost the num_ctx number it still doesn't answer anything, when the prompt is too long there is no output, is this model related?

<!-- gh-comment-id:2058163356 --> @17Reset commented on GitHub (Apr 16, 2024): Again it doesn't work, even if I boost the num_ctx number it still doesn't answer anything, when the prompt is too long there is no output, is this model related?
GiteaMirror commented 2026-04-12 12:31:19 -05:00
Author
Owner
Copy Link

@realquatro commented on GitHub (Apr 29, 2024):

Hi there, the context window defaults to 2048 and can be overridden with the num_ctx option: https://github.com/ollama/ollama/blob/main/docs/api.md#generate-request-with-options

It does work on http://localhost:11434/api/generate 。
But how can I increase the context window when I use http://localhost:11434/v1/chat/completions ?

<!-- gh-comment-id:2082198464 --> @realquatro commented on GitHub (Apr 29, 2024): > Hi there, the context window defaults to 2048 and can be overridden with the `num_ctx` option: https://github.com/ollama/ollama/blob/main/docs/api.md#generate-request-with-options It does work on http://localhost:11434/api/generate 。 But how can I increase the context window when I use http://localhost:11434/v1/chat/completions ?
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
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#2247
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?